ds-ship
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to act autonomously on feedback from external sources, which presents a surface for indirect instructions to be processed by the agent.
- Ingestion points: The skill monitors and responds to pull request findings, automated review bot messages, and human review comments as described in Steps 6 and 7 of SKILL.md.
- Boundary markers: The instructions provide a logical boundary by directing the agent to "Keep scope fixed" and "Decline extra work from reviews."
- Capability inventory: The agent has the ability to modify source code, execute tests, push changes to remote branches (including force-pushing), and merge pull requests.
- Sanitization: The skill does not define specific methods for sanitizing or escaping the text content received from reviews or logs before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill requires the agent to execute various shell commands to perform its core functions.
- Evidence: Step 3 explicitly instructs the agent to run tests and application checks, pasting the command and output into notes. Step 7 involves executing merge operations using the repository's standard methods.
Audit Metadata