Skip to main content
Run any Skill in Manus
with one click
maruakshay
GitHub creator profile

maruakshay

Repository-level view of 58 collected skills across 1 GitHub repositories.

skills collected
58
repositories
1
updated
2026-04-30
repository map

Where the skills live

Top repositories by collected skill count, with their share of this creator catalog and occupation spread.

repository explorer

Repositories and representative skills

agent-memory-poisoning
information-security-analysts

Review agentic AI systems for long-term memory store poisoning, vector DB manipulation, cross-session instruction injection, and stale memory exploitation that persists attacker influence across agent sessions.

2026-04-30
ai-agent-identity-authz
information-security-analysts

Review AI agent systems for agent impersonation, capability escalation, missing agent identity primitives, and authorization failures that allow agents to act beyond their granted permissions or impersonate other agents or human users.

2026-04-30
ai-assisted-social-engineering
information-security-analysts

Review organizational defenses against AI-assisted spearphishing, voice cloning, synthetic identity fraud, deepfake executive impersonation, and AI-accelerated reconnaissance that dramatically lowers the barrier to highly targeted social engineering attacks.

2026-04-30
ai-content-authenticity
information-security-analysts

Review AI-generated content pipelines for deepfake detection gaps, provenance chain failures, C2PA implementation correctness, synthetic media attribution, and trust signal spoofing that undermines content authenticity verification.

2026-04-30
browser-agent-security
information-security-analysts

Review AI browser agents for DOM injection attacks, credential harvesting via web automation, malicious web content that hijacks agent actions, session cookie theft, and phishing sites engineered to exploit browser-controlling AI agents.

2026-04-30
dataset-supply-chain-security
information-security-analysts

Review upstream dataset integrity controls, HuggingFace repository risks, dataset versioning, dependency pinning, and third-party dataset provenance to prevent malicious data from entering training or RAG pipelines.

2026-04-30
human-in-the-loop-bypass
information-security-analysts

Review AI agent systems for approval step circumvention, human-in-the-loop bypass patterns, deferred confirmation exploitation, and social engineering techniques that cause human reviewers to approve malicious agent actions.

2026-04-30
inference-api-abuse-prevention
information-security-analysts

Review inference APIs for credential stuffing, rate limit bypass, quota exhaustion, account takeover, and systematic abuse patterns that exploit the high cost-per-request nature of LLM inference.

2026-04-30
Showing top 8 of 58 collected skills in this repository.
Showing 1 of 1 repositories
All repositories loaded