Skills
skills/team-attention/hoyeon/compound/Gen Agent Trust Hub

compound

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected.
  • Ingestion points: Pull request comments and reviews are fetched using the gh tool; local context files (learnings.json, decisions.md, issues.json) are read from the .hoyeon/specs/ directory.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to ignore potentially malicious content within the ingested Pull Request data.
  • Capability inventory: The skill uses Bash for data collection and the Write and Edit tools to create or modify documentation files.
  • Sanitization: No sanitization or validation of the external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 11:01 AM