dev-spec

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by ingesting external data and incorporating it into a generated file. * Ingestion points: Reads 'the idea' and 'prior lens outputs' as specified in Step 1 of SKILL.md. * Boundary markers: The instructions do not define delimiters or specific safety instructions to ignore embedded commands within the ingested ideas. * Capability inventory: The skill has the capability to write files to the local workspace path ('<workspace_path>/ideas//analysis/dev-spec.md'). * Sanitization: No sanitization or validation of the input content is performed before generating the specification.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 11:23 PM
Security Audit — agent-trust-hub — dev-spec