authoring-prd

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill's primary function is to ingest external, untrusted data (product ideas, change requests, and upstream documents) and elaborate on it. This creates a surface for indirect prompt injection, where an attacker could embed instructions in the product idea to manipulate the agent's behavior or output.
  • Ingestion points: External data enters the context via the 'project idea' and 'upstream context documents' defined in the Inputs section of SKILL.md.
  • Boundary markers: The instructions lack specific guidance on using delimiters or ignore-instructions to isolate the untrusted user input from the skill's logic.
  • Capability inventory: The skill uses a deep-research capability, a PRD template tool, and performs markdown text generation.
  • Sanitization: There is no evidence of sanitization or validation of the input data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 11:37 AM
Security Audit — agent-trust-hub — authoring-prd