code-quality-analyzer

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: No security issues detected. The skill's instructions and metadata are consistent with its stated purpose as a code quality analysis service.\n- [NO_CODE]: The skill does not provide any scripts, binaries, or executable logic; it relies entirely on the agent's inherent capabilities to follow instructions provided in the markdown body.\n- [PROMPT_INJECTION]: The skill's primary function involves processing external code, which inherently creates a surface for indirect prompt injection if the processed content contains adversarial instructions.\n
  • Ingestion points: Processes untrusted code from direct user input and reads from local file paths specified in SKILL.md.\n
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted code from the agent's system instructions.\n
  • Capability inventory: The skill description implies the agent has read access to the local filesystem for project-level analysis.\n
  • Sanitization: No methods for sanitizing, validating, or filtering the content of the analyzed files are implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 03:45 AM
Security Audit — agent-trust-hub — code-quality-analyzer