write-local-report

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by processing untrusted data from the local project environment.
  • Ingestion points: The agent reads previous report files from the .github/reports/ directory and source code/test files from src/ and tests/ to generate summaries.
  • Boundary markers: The skill relies on Markdown structural elements but lacks explicit delimiters or instructions to the agent to ignore potentially malicious directions embedded in the ingested files.
  • Capability inventory: The skill allows the agent to write new files to the repository.
  • Sanitization: There are no mechanisms described for sanitizing or filtering instructions that may be hidden in code comments or previous reports.
  • [COMMAND_EXECUTION]: The project template includes shell commands for code linting and testing (black, flake8, pytest). While these are standard tools in a development environment, they constitute an execution surface if the agent attempts to run them on maliciously crafted source or test files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:29 PM