course-outline-market-positioning

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates an Indirect Prompt Injection surface by ingesting untrusted data.
  • Ingestion points: Processes user-supplied course outlines, uploaded files, and content from external benchmark links as defined in references/form-schema.json.
  • Boundary markers: No explicit delimiters or instructions are provided in the skill to warn the agent about potential instructions embedded within the processed data.
  • Capability inventory: The skill uses scripts/run.py to transmit the collected data to the vendor's API (https://ai-skills.ai/api/execute).
  • Sanitization: There is no evidence of input sanitization or validation within the provided scripts to prevent malicious content from influencing the agent's behavior.
  • [COMMAND_EXECUTION]: The skill includes a Python runner script (scripts/run.py) designed to interact with the vendor's API.
  • Evidence: The script uses the urllib library to perform HTTP POST requests and includes logic for polling asynchronous execution results. It handles environment variables for authentication (AISKILLS_API_KEY).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:31 AM
Security Audit — agent-trust-hub — course-outline-market-positioning