skills/angusfretwell/skills/how/Gen Agent Trust Hub

how

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external codebase content which inherently creates an indirect prompt injection surface if source files contain malicious instructions disguised as comments.
  • Ingestion points: The skill dispatches explorer subagents to read and analyze source code as defined in SKILL.md and references/explorer-brief.md.
  • Boundary markers: The prompts do not specify the use of clear delimiters or instructions to ignore potential instructions embedded within code comments or documentation.
  • Capability inventory: The skill is focused on analysis and documentation synthesis; it does not include instructions for sensitive data exfiltration or arbitrary command execution.
  • Sanitization: The references/explorer-brief.md mandates that findings must be traced to specific file paths, function names, and line numbers, providing a factual grounding that helps mitigate the impact of adversarial content within the code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 03:34 PM
Security Audit — agent-trust-hub — how