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