tasks
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a purely analytical and documentation-focused workflow. The logic encourages sizing constraints and artifact-based verification, which promotes safe and predictable agent behavior. No obfuscation, data exfiltration, or unauthorized command execution was detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project documentation, which creates a potential surface for indirect prompt injection.
- Ingestion points: Reads files matching
design-docs/*.frame.mdand project alignment documents. - Boundary markers: None explicitly defined to separate ingested document content from instructions.
- Capability inventory: The skill performs text analysis and formatting, and recommends the use of the
task-creationtool. - Sanitization: No specific content filtering or sanitization is implemented for the ingested documentation.
Audit Metadata