add-functional-spec

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-controlled files to understand context and existing specs. This data ingestion creates a surface for indirect prompt injection, where malicious instructions embedded in the specification files could potentially influence the agent's behavior during the drafting or validation steps.
  • Ingestion points: Target .plain files read during the workflow (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore embedded commands within the specification data.
  • Capability inventory: The skill has the capability to write (append) content to the local file system and invokes several analysis and resolution tools.
  • Sanitization: No explicit sanitization or validation logic is described for the content read from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 08:40 AM
Security Audit — agent-trust-hub — add-functional-spec