implement
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from external sources (GitHub Issues) that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Fetches issue body and comments using
gh issue viewinSKILL.md. - Boundary markers: The instructions do not define clear delimiters or instruct the agent to ignore embedded commands within the fetched issue content.
- Capability inventory: The skill has the ability to execute shell commands (typechecking, tests, GitHub CLI), read sensitive documentation files, and commit changes to the repository as seen in
SKILL.md. - Sanitization: There is no mention of sanitizing or validating the content retrieved from GitHub before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses the
gh(GitHub CLI) tool and expects to run project-specific typecheckers and test suites. - Evidence:
gh issue view <number> --json number,title,body,labels,commentsand instructions to run tests and typechecking inSKILL.md. - Context: These are standard operations for a software implementation skill and use a well-known service (GitHub).
Audit Metadata