ack-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted review reports.
  • Ingestion points: Reads from $ARGUMENTS and files like 'review.md' or 'findings.md' (SKILL.md).
  • Boundary markers: Absent; does not use delimiters or instructions to ignore embedded instructions.
  • Capability inventory: Modifies files (Step 5) and executes shell commands (Step 6).
  • Sanitization: Absent; no validation is performed on report contents.
  • [COMMAND_EXECUTION]: The skill executes shell commands to run unit tests and linters (Step 6), which can be abused to execute malicious code if influenced by the review report.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 03:28 PM