create-topic-note

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Detected an indirect prompt injection surface where the skill ingests untrusted data from user notes to perform automated file operations.
  • Ingestion points: The skill reads frontmatter and content from user-specified notes and discovered related notes in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate note content from agent instructions during processing.
  • Capability inventory: The skill creates new markdown files in 03-Records/Topics/ and modifies the related property in the frontmatter of existing notes (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the ingested note content before it is synthesized into summaries or tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 11:37 PM
Security Audit — agent-trust-hub — create-topic-note