implement-specs
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from GitHub issues and pull requests, which can be authored by untrusted external parties.
- Ingestion points: The
scripts/fetch_github_context.pyscript fetches issue bodies, PR descriptions, and comments. TheSKILL.mdinstructions also reference local context files such asissue_context.json,issue_comments.txt, andpr_diff.txt. - Boundary markers: The script implements a provenance system by wrapping fetched content in headers that include metadata such as the source, author, and
author_association. It explicitly marks content from trusted roles (OWNER, MEMBER, COLLABORATOR) with atrust=TRUSTEDlabel. - Capability inventory: The skill enables the agent to write implementation code and update repository specifications. The helper script uses
subprocess.runto interact with the GitHub CLI (gh). - Sanitization: No content-level sanitization (e.g., stripping markdown or HTML comments) is performed on the fetched data. The skill relies on the agent following instructions to treat this content as data rather than instructions.
- [COMMAND_EXECUTION]: The Python script
scripts/fetch_github_context.pyexecutes shell commands using thesubprocessmodule to interact with the GitHub CLI. - Evidence: It uses
subprocess.run(["gh", *args], ...)andsubprocess.run(["gh", "pr", "diff", ...], ...)to fetch data. - Context: These calls use argument lists rather than shell strings, which is a safe practice that prevents command injection from the repository or number parameters.
Audit Metadata