ai-ship
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process content from GitHub issue bodies, which are external data sources that could potentially contain malicious instructions.
- Ingestion points: Fetches issue title, labels, and body content via
gh issue list(SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the issue data.
- Capability inventory: The agent can execute shell commands (
pnpm,gh,npx), write or modify files in the repository, and create/comment on pull requests. - Sanitization: There is no evidence of sanitization or filtering of the issue content before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill executes various command-line tools such as
gh,pnpm,npx, andtscto manage the development lifecycle. These commands are necessary for the skill's stated purpose and operate on the local repository environment.
Audit Metadata