Triage eligible fetch
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
fetch.pyusessubprocess.runto execute the GitHub CLI tool (gh). This is used to perform GraphQL API queries for fetching issue and pull request data. The command is constructed as a list, mitigating standard shell injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources (GitHub) which could contain malicious instructions designed to alter the agent's behavior during triage.
- Ingestion points: Fetches issue titles, pull request bodies, and user comments via GraphQL in
fetch.py(e.g., inpaginate_nodesandbackfill_comments). - Boundary markers: None identified. The fetched text data is not enclosed in delimiters or accompanied by instructions for the agent to ignore embedded prompts.
- Capability inventory: The skill has the ability to execute shell commands via the
ghCLI (found infetch.py). - Sanitization: The script does not sanitize or validate the text content retrieved from GitHub before returning it in JSON format to the agent context.
Audit Metadata