course-operations-manual

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on structured text generation for course management. Analysis of the instructions reveals no hidden commands, obfuscation, or persistence mechanisms.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via the input_pdf and --course parameters. Maliciously crafted input data could attempt to influence the agent's output behavior.
  • Ingestion points: Processes user-provided PDF documents (input_pdf) and command-line arguments (--course).
  • Boundary markers: The instructions do not define specific delimiters or "ignore instructions" guards for the parsed content.
  • Capability inventory: The skill is restricted to text generation and internal chaining to a document generator; it lacks file system access, shell execution, or network capabilities.
  • Sanitization: There is no evidence of input validation or sanitization for the content extracted from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:27 AM
Security Audit — agent-trust-hub — course-operations-manual