ln-610-docs-auditor

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted project documentation and web research, creating a surface for indirect prompt injection.
  • Ingestion points: The workflow involves discovering documentation surfaces and performing web research as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions.
  • Capability inventory: The coordinator delegates tasks to child worker skills (ln-611, ln-612, ln-613, ln-614) via the Skill tool, which performs various auditing functions.
  • Sanitization: No evidence of sanitization or validation of the ingested content is specified in the instruction logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 06:07 PM