spec-writing
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function includes auditing existing specification files within the 'specs/' directory. This interaction represents an indirect prompt injection surface where instructions embedded in the user-provided specification text could attempt to override the agent's behavior during analysis.\n
- Ingestion points: Specification files (typically markdown) in the 'specs/' folder are read and processed during the 'Specs Audit Mode' (Phase 5).\n
- Capability inventory: The skill is authorized to use the platform's 'Agent' tool to deploy up to 100 parallel subagents for auditing purposes and possesses the capability to modify local files ('auto-fix').\n
- Boundary markers: The instructions do not include specific delimiters or warnings to the agent to treat the content of these external files as untrusted data.\n
- Sanitization: There is no evidence of filtering or sanitization logic to detect or neutralize malicious instructions embedded within the specification content.
Audit Metadata