decision-mapping
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process data from external 'map artifacts' (such as issue tracker pages or Markdown files) which represents a potential surface for indirect prompt injection.
- Ingestion points: The agent is directed to load map artifacts from paths or URLs and read ticket bodies during the resolution workflow in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instruction' warnings when the agent processes the content of these external tickets.
- Capability inventory: The skill's primary function is organizing and updating the decision map; while it coordinates other activities like research and prototyping, it does not include direct dangerous capabilities like arbitrary shell execution or network exfiltration within its own instruction set.
- Sanitization: There are no instructions provided to sanitize, validate, or filter the content retrieved from external maps or tickets before the agent incorporates it into its decision-making process.
Audit Metadata