skill-quality-review

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute git commands to resolve file paths for review.
  • Evidence: 'git diff --name-only ... -- 'skills/**/SKILL.md'' in SKILL.md.\n- [PROMPT_INJECTION]: The skill ingests and processes untrusted skill instructions from third-party SKILL.md files, creating a vulnerability surface for indirect prompt injection.
  • Ingestion points: Reads the target SKILL.md, any referenced files in references/, and scripts/ identified during the audit process.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' warnings for the ingested content.
  • Capability inventory: The agent can execute git commands and read arbitrary files within the repository.
  • Sanitization: Absent. The content is processed directly for qualitative evaluation without filtering or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 04:15 PM
Security Audit — agent-trust-hub — skill-quality-review