gh-daily-timeline
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script executes the GitHub CLI (
gh) andjqlocally to retrieve user events and format output. This is a standard and necessary operation for the skill's functionality. - [PROMPT_INJECTION]: The skill processes untrusted external data (commit messages, issue titles, PR descriptions) which could contain adversarial instructions designed to influence the behavior of the AI agent processing the report.
- Ingestion points: The script
gh-activity.shfetches data from the GitHub API via thegh apicommand. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious content within the retrieved data.
- Capability inventory: The skill uses the
ghCLI, which is authenticated to the user's account and has network access to GitHub. - Sanitization: No sanitization or filtering is applied to the text fields retrieved from the API before they are printed to the output.
Audit Metadata