qa-nfr-analyst

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data including requirements documents, stakeholder input, and source code to generate NFR specifications. This creates a surface for indirect prompt injection where malicious instructions embedded in these inputs could attempt to influence the agent's analysis or documentation output.
  • Ingestion points: Identified in SKILL.md under the 'Scope' section, which states the agent can "Analyze NFRs from requirements docs, stakeholder input, or code."
  • Boundary markers: Absent. The instructions do not define specific delimiters (like XML tags or triple quotes) or provide 'ignore embedded instructions' directives to isolate external content from the system prompt.
  • Capability inventory: The skill is restricted to analysis and markdown document generation. There are no identified capabilities for network operations, arbitrary command execution (subprocess calls), or writing to sensitive file paths.
  • Sanitization: Absent. The skill does not explicitly instruct the agent to escape or validate external content before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:38 PM
Security Audit — agent-trust-hub — qa-nfr-analyst