constructive-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions in markdown format. It does not include any scripts, executables, or configuration files that could perform actions on the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data by reviewing code diffs and pull request descriptions provided by users.
  • Ingestion points: User-pasted code diffs and PR metadata (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded within the code being reviewed.
  • Capability inventory: The skill itself has no capabilities to write files, execute commands, or access the network; its purpose is solely to guide the phrasing of text feedback.
  • Sanitization: No sanitization methods are defined, but as the output is restricted to qualitative review comments, the impact of potential injection is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 03:56 PM
Security Audit — agent-trust-hub — constructive-code-review