菜单
Use when the developer asks about secrets, credentials, API keys, or tokens found in their code, or wants to understand secret scanning results. Auto-triggers on: "found secrets", "are there secrets", "credential scan", "API key detected", "what secrets", "leaked keys", "scan for secrets".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Seeds per-session canary tokens into WebFetch advisories and scans every subsequent tool input/output for the canary's appearance. Use when the developer wants prompt-injection detection telemetry, or asks "is my session compromised?". Auto-fires on PreToolUse(WebFetch) and PostToolUse(*). Do not use for in-prompt sanitization (see deep-research's <untrusted_source> wrapping).
Detects subagent capability escapes by comparing the tool being invoked against the skill's declared allowed-tools list. Use when the developer asks about subagent escape, sees a tool fired from an unexpected skill, or audits delegation.md compliance. Auto-fires on PreToolUse. Best-effort observability only — does not block.
OPT-IN BLOCKING capability allowlist. Pairs with hydra-capability-fence (advisory). When state/capability-policy.json sets enabled:true, this shield blocks any tool call whose name is not in the active SKILL.md frontmatter allowed-tools list. Use when the developer asks why a tool call was blocked, wants to enable or tune the capability allowlist, or reviews a stderr "capability-shield (BLOCKED)" message. Default disabled — out of the box this shield does nothing. Do not use for observability without enforcement (see capability-fence).
Logs every WebFetch / WebSearch / Bash-network destination to an append-only NDJSON and surfaces first-seen domains as advisory warnings. Use when the developer asks "what did this session reach out to?" or "show me egress", wants a per-session list of contacted hosts, asks about an egress-monitor advisory, or wants to inspect state/log.ndjson. Auto-fires on PostToolUse for network tools. Do not use for in-process state inspection (see audit-trail).
OPT-IN BLOCKING egress allowlist. Pairs with hydra-egress-monitor (advisory). When state/egress-policy.json sets enabled:true, this shield blocks any WebFetch / WebSearch / Bash-network call whose destination host is not in the operator-curated allowlist. Use when the developer asks why a network call was blocked, wants to inspect or edit the egress allowlist, or asks about audit.ndjson policy_blocked events. Default disabled — out of the box this shield does nothing. Do not use for observability without enforcement (see egress-monitor).
Scans the project's dep tree for license compatibility against an allow/deny policy. Use when the developer asks "what licenses are in here?" or before a release. Reports denied (GPL/AGPL/SSPL), warned (MPL/EPL/CDDL), and allowed (MIT/Apache/BSD/ISC) classifications. Do not use for license-text generation (see SBOM).
| name | secret-awareness |
| description | Use when the developer asks about secrets, credentials, API keys, or tokens found in their code, or wants to understand secret scanning results. Auto-triggers on: "found secrets", "are there secrets", "credential scan", "API key detected", "what secrets", "leaked keys", "scan for secrets". |
| allowed-tools | ["Read","Grep","Bash"] |
<decision_tree> IF user asks about a specific secret finding: → Read ${CLAUDE_PLUGIN_ROOT}/state/audit.jsonl → grep for "secret_detected" events → Filter to relevant file → Show: pattern_id, severity, masked value, line number → Suggest remediation: move to .env, use vault, rotate key
IF user asks for full scan: → Run: python3 ${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/pattern-engine.py . → Show summary grouped by severity and category → Prioritize critical findings first
IF user asks about entropy findings: → Run: python3 ${CLAUDE_PLUGIN_ROOT}/../../shared/scripts/entropy-analyzer.py → Show: high-entropy strings with entropy score → Explain: "These strings have high randomness (>4.5 bits/char) and may be secrets"
IF no findings: → "No secrets detected. Hydra monitors every Write/Edit for 200+ patterns." </decision_tree>
<output_format>
| File | Line | Pattern | Masked | Action |
|---|---|---|---|---|
| ... | ... | ... | ... | Rotate + move to .env |
...
...
Summary: [N] secrets found | [N] files affected | [critical count] need immediate rotation </output_format>
<escalate_to_sonnet> IF more than 10 distinct secret types found: "ESCALATE_TO_SONNET: complex secret remediation plan needed" IF secrets found in production config files: "ESCALATE_TO_SONNET: production secret exposure — incident response guidance needed" </escalate_to_sonnet>
