implement
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted data from user-provided specifications and tickets, as well as the repository's
CONTRIBUTING.mdfile. - Ingestion points: User-supplied implementation briefs/tickets and the local
CONTRIBUTING.mdfile are read and processed by the agent to guide its actions. - Boundary markers: The instructions lack specific delimiters or boundary markers to separate instructional commands from the data being processed, which may lead the agent to follow instructions embedded within the specification.
- Capability inventory: The skill has broad capabilities including file system modification (creating branches and commits) and shell command execution (running typecheckers and test suites).
- Sanitization: No sanitization or validation steps are defined for the input data, relying on the agent's internal guardrails to distinguish between implementation details and potential malicious instructions.
Audit Metadata