ds-adopt
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including pull request descriptions, commit messages, and review comments. • Ingestion points: Reads descriptions, commits, and comments from the target PR or branch as described in SKILL.md. • Boundary markers: No explicit instructions are given to use delimiters or ignore instructions embedded within the PR data. • Capability inventory: The skill uses tools like ds-revive and ds-pr, and executes the workflow of the adopted branch. • Sanitization: No sanitization or validation of the ingested external content is mentioned.
- [COMMAND_EXECUTION]: The instructions require the agent to run the 'real workflow' of the inherited codebase to verify the goal, which involves executing scripts or tests from the potentially untrusted source branch.
Audit Metadata