1k-pr-daily-report
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gh pr listto retrieve pull request metadata including titles, states, and authors from GitHub repositories. This is consistent with the skill's primary function of generating activity reports. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external GitHub pull request titles and descriptions. 1. Ingestion points: Fetches data from GitHub via the
ghtool as defined inSKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or instructions for the agent to ignore potentially malicious content within PR titles. 3. Capability inventory: The agent is tasked with summarizing and translating external content into a structured report. 4. Sanitization: No input sanitization is performed on the data before it is presented to the agent for processing.
Audit Metadata