doc-learner

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The core functionality of the skill involves ingesting and analyzing user-provided documents to extract structural and stylistic patterns as described in the workflow in SKILL.md.\n
  • Ingestion points: User-provided documents and prompt samples used for learning (referenced in Phase 1 of SKILL.md).\n
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input text provided by the user.\n
  • Capability inventory: The skill's output is limited to generating text, templates, and prompts; it has no direct network, file-system, or command execution capabilities.\n
  • Sanitization: There is no evidence of input validation or sanitization for the analyzed content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 06:17 AM