sdd-propose

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as user descriptions and exploration analysis to generate change proposals, creating a potential vector for indirect prompt injection.
  • Ingestion points: The skill accepts 'direct user description' and 'Exploration analysis' as inputs according to the 'What You Receive' section in SKILL.md.
  • Boundary markers: The template for 'proposal.md' in Step 4 uses simple string interpolation for placeholders like {Intent} and {Scope} without explicit delimiters or instructions to the agent to disregard embedded commands in the input data.
  • Capability inventory: The skill has the capability to write to the filesystem to create change directories and 'proposal.md' files (SKILL.md, Step 2 and Step 4).
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the provided text before it is written to the project artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:38 PM
Security Audit — agent-trust-hub — sdd-propose