implement
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as specifications and tickets, which creates a potential surface for indirect prompt injection.
- Ingestion points:
SKILL.mdspecifies that the agent should implement work based on "spec or ticket" provided by the user. - Boundary markers: There are no explicit instructions or delimiters mentioned to isolate the spec/ticket content from the agent's core instructions.
- Capability inventory: The skill allows for tool invocation ("tdd", "code-review"), local command execution (type checks and tests), and file system modification (committing to the current branch).
- Sanitization: No sanitization or validation logic is present for the input data.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute type checks and test suites on local files. This is a standard and expected capability for a developer-oriented skill.
Audit Metadata