breakdown-test
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily a prompt template for generating documentation. It does not include executable code, scripts, or external dependencies.- [PROMPT_INJECTION]: No patterns of instruction override, safety filter bypass, or role-play jailbreaks were detected. The use of a professional persona is consistent with its stated purpose.- [DATA_EXFILTRATION]: The skill interacts with local project documentation files for context but does not contain commands for network transmission, credential access, or unauthorized file reads.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external project documents (PRDs, technical breakdowns) at runtime. However, the impact is negligible as the agent's actions are limited to text generation and markdown output.
- Ingestion points: Reads feature documentation from specified file paths.
- Boundary markers: No explicit delimiters or isolation warnings are provided for the input data.
- Capability inventory: Restricted to text analysis and markdown generation.
- Sanitization: No filtering or validation of external content is performed.
Audit Metadata