report-implementation

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests content from GitHub issue descriptions, comments, and local repository files to drive its report generation and verification logic.
  • Ingestion points: Uses gh issue view to read issue data and git diff or file reads to inspect repository state as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to isolate untrusted external content from the agent's internal logic.
  • Capability inventory: The skill possesses the ability to execute shell commands discovered in the repository and perform write actions to GitHub issues using the gh CLI.
  • Sanitization: There are no instructions for sanitizing or validating external input before it is interpolated into command discovery or reporting drafts.
  • [COMMAND_EXECUTION]: The skill is designed to automatically identify and execute verification commands found in project documentation, package.json, or other configuration files. This creates a surface where a malicious repository could trigger the execution of arbitrary code during the verification gate process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 08:56 AM
Security Audit — agent-trust-hub — report-implementation