Run any Skill in Manus with one click

sharp-edges

Stars0

Forks0

UpdatedMay 29, 2026 at 02:51

Find footgun APIs, dangerous defaults, and misuse-prone designs (where the secure path isn't the default). The sharp-edges-analyzer agent reasons through three adversaries (scoundrel / lazy dev / confused dev) across six categories and promotes real edges into .kuzushi/findings.json (source "sharp-edges"). Distinct from /sast (injection) and the insecure-defaults companion (config values).

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

allsmog

allsmog/kuzushi-security-plugin

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	sharp-edges
description	Find footgun APIs, dangerous defaults, and misuse-prone designs (where the secure path isn't the default). The sharp-edges-analyzer agent reasons through three adversaries (scoundrel / lazy dev / confused dev) across six categories and promotes real edges into .kuzushi/findings.json (source "sharp-edges"). Distinct from /sast (injection) and the insecure-defaults companion (config values).
context	fork
agent	sharp-edges-analyzer
user-invocable	false

Sharp edges

Find the APIs and configs where it's easy to be insecure — secure usage should be the path of least resistance.

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/sharp-edges-prepare.mjs" --target "<repo root>" (optionally --input '{"maxCandidates":30}'). If it reports no-candidates, say so and stop. Read the prep's prepPath.
For each candidate, open the site and reason through the three adversaries (scoundrel / lazy dev / confused dev) across the six categories (algorithm-selection, dangerous-defaults, primitive-vs-semantic, configuration-cliff, silent-failures, stringly-typed-security). Decide finding / candidate / rejected.
Write the { candidates: [...] } bundle to the prep's draftPath, then run the assembleCommand — it validates verdicts/categories and promotes them into .kuzushi/findings.json (source:"sharp-edges").
Report findings by category (file:line, the adversary, the safer-by-default API to prefer).

When NOT to use

For injection / source→sink bugs — that's /sast and /taint-analysis.
For hardcoded secrets / config values — that's the insecure-defaults companion; here the concern is the API/config shape that invites misuse.

Rationalizations to Reject

"Used correctly here, so fine." → The edge is that it's easy to use wrong; insecure-by-default is still a finding even if this call site is OK.
"It's just a default." → The scoundrel/lazy dev won't fix it; insecure-by-default is the bug.
"Scary but unprovable." → That's candidate, not finding — and not silently dropped.

More from this repository

same repository

deep-hunt

allsmog/kuzushi-security-plugin

Interprocedural, hypothesis-driven hunt — finds the multi-file source→sink bugs that pattern-gating and same-file taint miss. Ranks trace anchors (entry points + dangerous sinks), then the deep-hunter agent walks each flow ACROSS files (forward/backward call-graph CLIs) over multiple rounds, confirming propagation and defeating guards, and promotes confirmed cross-file flows into findings.json with the path stored as evidenceGraph. Token-expensive, budget-bounded. Part of the HUNT phase (run via /sweep --deep, or ask for it); leads flow to /verify (panel).

2026-06-110

deep-scan

allsmog/kuzushi-security-plugin

Whole-file deep reader — finds bugs by READING risk-ranked files in full and reasoning from first principles, not by grepping for known patterns. Catches the long tail (project-specific wrappers, business logic, cross-function flaws) that pattern-gated producers structurally miss. Token-expensive; budget-bounded and risk-ranked. Promotes leads into .kuzushi/findings.json (source "deep-scan").

2026-06-110

taint-analysis

allsmog/kuzushi-security-plugin

IRIS-style source→sink taint hunt. Ranks a typed CWE catalog for the repo, then drives subagents to label dangerous sinks, label sources of user input, run Joern/CodeQL dataflow queries (or same-file linking) to connect them, and triage each flow as finding/candidate/rejected. Promotes verdicts into .kuzushi/findings.json. Benefits from a prebuilt CodeQL DB / Joern CPG but degrades gracefully.

2026-06-110

threat-hunt

allsmog/kuzushi-security-plugin

Adversarial per-threat review (Carlini doctrine). For each threat in .kuzushi/threat-model.json, state attacker capabilities, walk source→sink, attempt to bypass every guard, and assign a verdict with evidence. Promotes findings into .kuzushi/findings.json. Requires /threat-model first.

2026-06-110

partition

allsmog/kuzushi-security-plugin

Split the attack surface into parallel-discovery partitions so fan-out hunters explore different subsystems instead of converging on the same shallow bug. Deterministic grouping of /x-ray entry points by component → .kuzushi/partitions.json, which a hunt coordinator hands to one subagent per partition. Run /x-ray first.

2026-06-100

poc

allsmog/kuzushi-security-plugin

Empirical proof-of-concept for the PoC-ready findings. For each finding /verify marked confirmed-exploitable or inconclusive, synthesize a minimal harness that triggers the bug; a host script then runs it in a sandbox (Docker --network none when present, else a gated local run) and classifies the crash into a proof verdict. Attaches a poc block onto each finding. Requires /verify first.

2026-06-100

name	sharp-edges
description	Find footgun APIs, dangerous defaults, and misuse-prone designs (where the secure path isn't the default). The sharp-edges-analyzer agent reasons through three adversaries (scoundrel / lazy dev / confused dev) across six categories and promotes real edges into .kuzushi/findings.json (source "sharp-edges"). Distinct from /sast (injection) and the insecure-defaults companion (config values).
context	fork
agent	sharp-edges-analyzer
user-invocable	false

Sharp edges

Find the APIs and configs where it's easy to be insecure — secure usage should be the path of least resistance.

Run node "${CLAUDE_PLUGIN_ROOT}/scripts/cmd/sharp-edges-prepare.mjs" --target "<repo root>" (optionally --input '{"maxCandidates":30}'). If it reports no-candidates, say so and stop. Read the prep's prepPath.
For each candidate, open the site and reason through the three adversaries (scoundrel / lazy dev / confused dev) across the six categories (algorithm-selection, dangerous-defaults, primitive-vs-semantic, configuration-cliff, silent-failures, stringly-typed-security). Decide finding / candidate / rejected.
Write the { candidates: [...] } bundle to the prep's draftPath, then run the assembleCommand — it validates verdicts/categories and promotes them into .kuzushi/findings.json (source:"sharp-edges").
Report findings by category (file:line, the adversary, the safer-by-default API to prefer).

When NOT to use

For injection / source→sink bugs — that's /sast and /taint-analysis.
For hardcoded secrets / config values — that's the insecure-defaults companion; here the concern is the API/config shape that invites misuse.

Rationalizations to Reject

"Used correctly here, so fine." → The edge is that it's easy to use wrong; insecure-by-default is still a finding even if this call site is OK.
"It's just a default." → The scoundrel/lazy dev won't fix it; insecure-by-default is the bug.
"Scary but unprovable." → That's candidate, not finding — and not silently dropped.