setup-ouyangjiahong-skills

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including repository configuration files (CLAUDE.md, CONTEXT.md) and issue tracker content (issue bodies and comments via gh/glab). This creates a vulnerability surface where malicious instructions embedded in these external sources could potentially influence the agent's behavior.
  • Ingestion points: Reads output from git remote -v, .git/config, CLAUDE.md, CONTEXT.md, and issue tracker comments via gh or glab commands.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the prompt logic.
  • Capability inventory: The skill has the ability to read and write files within the repository and execute CLI tools (git, gh, glab).
  • Sanitization: No sanitization or validation of the ingested content is mentioned before it is processed or used to generate new documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:04 AM
Security Audit — agent-trust-hub — setup-ouyangjiahong-skills