summarizing-shipped-work
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/fetch-shipped-prs.shto perform data retrieval. This script relies ongh(GitHub CLI) andjqbeing available on the system path for searching and filtering pull request data.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data in the form of pull request titles and descriptions sourced from GitHub.\n - Ingestion points: Pull request metadata and body text are ingested via the
gh search prscommand in thescripts/fetch-shipped-prs.shfile.\n - Boundary markers: The skill does not implement clear delimiters or instructions to ignore embedded commands when the agent processes the fetched JSONL data.\n
- Capability inventory: The skill has read access to GitHub data and provides summarization capabilities to the agent.\n
- Sanitization: The extraction script performs basic cleanup, such as stripping HTML comments and truncating the body to 400 characters, but does not sanitize against potential natural language instructions hidden in the PR content.
Audit Metadata