project-brief

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes technical specifications which are external data sources. This creates a surface where instructions embedded within the spec could potentially influence the agent's behavior, although this is a standard risk for document processing tasks.
  • Ingestion points: Technical specification files read via the Read tool in Step 1.
  • Boundary markers: The skill does not employ specific delimiters or 'ignore instructions' headers when passing the spec content to the subagent.
  • Capability inventory: The skill has access to Read, Write, and Agent tools.
  • Sanitization: No explicit sanitization or filtering is performed on the input file content prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 01:44 PM
Security Audit — agent-trust-hub — project-brief