skills/poteto/plugins/weekly-review/Gen Agent Trust Hub

weekly-review

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes commit messages and diffs which are external, potentially untrusted sources of data. * Ingestion points: Commit messages and diff data retrieved via git (SKILL.md). * Boundary markers: Absent; the instructions do not specify delimiters or provide warnings to the agent to disregard instructions contained within the commit metadata. * Capability inventory: The skill workflow utilizes git read commands; while not explicitly requesting network tools, the platform context may provide them. * Sanitization: None detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:44 PM
Security Audit — agent-trust-hub — weekly-review