tdd
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The
SKILL.mdfile contains a shell command!mkdir -p .claude && touch .claude/.tdd-active && echo "TDD marker created — enforcement hook active"executed at load time via the dynamic context injection syntax. This command is used for operational state tracking within the agent environment and is considered benign. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to drive code generation and testing cycles.
- Ingestion points: The planning phase in
SKILL.mdingests user-provided behavior descriptions and fix plans. - Boundary markers: The instructions lack explicit markers or warnings to ignore instructions embedded in the user-provided data.
- Capability inventory: The skill enables the agent to write files and execute test suites, alongside the load-time directory and file creation.
- Sanitization: No specific validation or sanitization of the user-provided behavioral descriptions is performed.
Audit Metadata