receiving-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes feedback from external sources, which creates a potential surface for indirect prompt injection. * Ingestion points: Code review feedback from external reviewers. * Boundary markers: The skill does not specify markers to separate untrusted feedback from its instructions. * Capability inventory: Includes the use of grep for searching and the GitHub CLI (gh api) for communication. * Sanitization: Input sanitization for review text is not described.
  • [COMMAND_EXECUTION]: The skill utilizes command-line tools such as grep and gh. These are used for the skill's primary tasks but provide a functional surface for the agent to interact with its environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 PM