sow-generator

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection by fetching data from the web and processing user-provided briefs without implementing boundary markers or sanitization.
  • Ingestion points: Data entering the agent context includes WebSearch results for client research and project briefs as outlined in references/required-inputs.md.
  • Boundary markers: The skill workflow lacks explicit delimiters or instructions to ignore embedded commands within the ingested research data.
  • Capability inventory: The agent has access to Bash, Write, Read, and WebSearch tools, which could be exploited to modify files or execute commands if a prompt injection occurs.
  • Sanitization: The instructions do not define a process for sanitizing or validating external content before it is processed and written to the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:26 AM
Security Audit — agent-trust-hub — sow-generator