gh-daily
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local git repository and the 'gh' GitHub CLI. It executes commands such as 'gh repo view', 'gh search issues', 'gh issue list', 'gh pr list', and 'git log' to gather activity data. These operations are within the stated scope of a standup report generator.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external, potentially untrusted sources (GitHub issues, pull requests, and notifications) which are then used to generate a report for the user.
- Ingestion points: Untrusted data enters the context through 'gh issue list', 'gh pr list', and 'gh api notifications' in 'SKILL.md'.
- Boundary markers: None; the skill does not define specific delimiters or instructions to the agent to treat external GitHub content as data-only or to ignore instructions embedded within that data.
- Capability inventory: The skill possesses shell execution capabilities ('gh', 'git', 'jq') and access to the user's authenticated GitHub session.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the content retrieved from GitHub (such as issue titles or labels) before it is interpolated into the final report generation logic.
Audit Metadata