github-discussion-query
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the GitHub CLI (
gh) and thejqutility to fetch and transform data. Evidence is present inquery-discussions.pyandquery-discussions.sh. Implementation uses safe argument passing (list-based in Python, quoted variables in Shell) to mitigate command injection risks. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from GitHub discussions.
- Ingestion points: Untrusted content is ingested from GitHub discussions via the
ghCLI in both the Python and Shell implementations. - Boundary markers: No specific delimiters or boundary instructions are used to separate external discussion content from agent instructions.
- Capability inventory: The skill possesses the capability to execute system commands (
gh,jq) via subprocess calls. - Sanitization: Discussion metadata and body content are returned to the agent without sanitization or escaping.
Audit Metadata