do-create-techspec
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources during its analysis phase, which could be exploited to influence the agent's behavior.
- Ingestion points: The skill reads product requirement documents at
prds/prd-[feature-slug]/prd.md(Step 2) and performs a deep analysis of the local codebase (Step 3). - Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the analyzed PRD or code files.
- Capability inventory: The agent possesses the capability to write files to the filesystem (
techspec.md), perform web searches, and interact with the user through theAskUserQuestiontool. - Sanitization: No explicit sanitization or filtering of the content read from the PRD or codebase is mentioned before it is processed for specification generation.
- [EXTERNAL_DOWNLOADS]: The skill includes a research step (Step 4) that utilizes the "Web Search" tool to gather framework information and business rules. This involves network activity to retrieve content from external, third-party sources.
Audit Metadata