execute-tdd-spec
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection as it ingests and processes content from external specification files.
- Ingestion points: The skill reads requirement and acceptance criteria data from files in the
.specs/directory (SKILL.md). - Boundary markers: Parsing is driven by specific section headers (Sections 4, 6, and 7) as specified in the workflow instructions (
SKILL.md). - Capability inventory: The skill allows the agent to write implementation code and execute test suites, build processes, and linting tools (
SKILL.md). - Sanitization: There is no explicit requirement for the agent to sanitize or ignore potential instructional content within the ingested specification files.
- [COMMAND_EXECUTION]: The skill requires the agent to run various shell-based tools for testing and validation, including test runners, linters, and type checkers (
SKILL.md). These are expected behaviors for a development-focused skill.
Audit Metadata