expand-learning-map

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied expansion objectives and existing Markdown lesson files, creating an attack surface where malicious instructions could be embedded in the content being analyzed.
  • Ingestion points: The skill ingests untrusted data via AskUserQuestion in Step 1 (expansion direction) and by reading existing roadmap.md and lessons/*.md files in Step 3.
  • Boundary markers: No explicit delimiters or instructions are used to separate ingested content from the system prompt, increasing the risk of the model following instructions hidden in the data.
  • Capability inventory: The skill possesses significant capabilities, including creating new files (Write tool in Step 5 and 6) and modifying existing files (Edit tool in Step 7 and 8) based on the processed content.
  • Sanitization: There is no evidence of content sanitization or validation to prevent prompt injection attacks from influencing the file-writing operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 05:13 AM
Security Audit — agent-trust-hub — expand-learning-map