announce
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gitandgh(GitHub CLI) commands to retrieve repository context, such as version tags, diffs, merged pull requests, and closed issues. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by ingesting and summarizing content from untrusted sources (pull requests and issues).
- Ingestion points: Untrusted data enters the context through
gh pr listandgh issue listcommands as specified inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit warnings to the agent to ignore potential instructions embedded within the retrieved PR or issue descriptions.
- Capability inventory: The skill is limited to read operations via
gitandghand generating text drafts. It does not include file-write, network exfiltration, or high-privilege execution capabilities. - Sanitization: There is no evidence of sanitization or filtering applied to the external data before it is processed by the agent.
Audit Metadata