capture-knowledge

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from source code entry points during its analysis and documentation workflow.
  • Ingestion points: Source code files, folder structures, function signatures, and API definitions specified for analysis (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions that may be embedded within the code being analyzed.
  • Capability inventory: The skill performs local file-write operations to create markdown documentation in the docs/ai/implementation/ directory (SKILL.md).
  • Sanitization: Absent. There is no evidence of sanitization or validation of the content extracted from the source entry points before it is synthesized into documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 02:20 PM