specifier
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as
pnpm type-check,pnpm test:integration, andmkdir. These commands are derived from the local repository's configuration (e.g.,package.json) and are executed during the validation phase to 'prove' the specification. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating an attack surface where malicious instructions could influence the agent's behavior.
- Ingestion points: GitHub ticket descriptions and pull request review comments fetched via the
gh apitool (documented in SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded instructions in the fetched content are present.
- Capability inventory: The skill can execute shell commands and perform network operations via the GitHub API to fetch and publish information.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the content retrieved from the issue tracker or PR comments.
Audit Metadata