spec-developer-v2

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is potentially vulnerable to indirect prompt injection because it reads untrusted content from a file (passed via $1) without implementing boundary markers or instructions to the agent to treat that content solely as data.
  • Ingestion points: Data is ingested from the file path provided in the first argument ($1).
  • Boundary markers: None. The prompt does not utilize delimiters or specific instructions to ignore embedded commands within the input.
  • Capability inventory: The skill employs the AskUserQuestionTool for user interaction and includes the ability to write a specification to a file.
  • Sanitization: There is no evidence of sanitization or escaping of the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 04:09 AM
Security Audit — agent-trust-hub — spec-developer-v2