why
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize standard development tools, specifically
gitandgh(GitHub CLI), to query repository history, commit metadata, and pull request discussions. These operations are scoped to read-only research tasks as defined in the skill documentation. - [INDIRECT_PROMPT_INJECTION]: The skill provides a mechanism for processing untrusted data sourced from repository records, which presents an attack surface for indirect prompt injection.
- Ingestion points: External data enters the agent's context through the output of commands like
git log,git show,gh api, andgh pr viewas specified inSKILL.md. - Boundary markers: The instructions do not include specific delimiters or instructions to ignore embedded commands within the retrieved git or PR metadata.
- Capability inventory: The skill's capabilities are restricted to read-only information retrieval from local and remote repository records; it does not contain functions for arbitrary code execution, persistence, or unauthorized data exfiltration.
- Sanitization: There is no evidence of filtering or sanitizing the content of commit messages, PR bodies, or issue discussions before they are presented to the agent.
Audit Metadata