tech-planner
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external feature specifications provided via a file path to generate technical documentation and Architecture Decision Records (ADRs).
- Ingestion points: The
SKILL.mdworkflow (Step 1) loads specification content from a user-provided path. - Boundary markers: There are no explicit instructions or delimiters used to separate the specification content from the agent's instructions, nor are there warnings to disregard instructions found within the spec.
- Capability inventory: The skill possesses file-read capabilities (accessing the spec) and file-write capabilities (creating new documentation in
specs/anddocs/adr/directories). - Sanitization: The skill does not implement validation or sanitization of the loaded specification content before it is used to drive the architectural analysis and document generation.
Audit Metadata