tdd-spec
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from PBIs, feature documents, and source code, which creates a surface for indirect prompt injection attacks where malicious instructions could be embedded in processed data.
- Ingestion points: The skill reads content from
team-artifacts/pbis/,src/Services/, anddocs/business-features/. - Boundary markers: No explicit delimiters or instructions are provided to the agent to differentiate between control instructions and data ingested from external files.
- Capability inventory: The skill uses
Bash(for grepping),Write, andEditto modify project documentation based on the results of its analysis. - Sanitization: There is no explicit sanitization or validation logic for the ingested external content.
- Human-in-the-loop: The risk is significantly mitigated by the mandatory use of
AskUserQuestionto review and approve test case lists before they are written to feature documents.
Audit Metadata