solution-candidate-design
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions aimed at influencing the agent's behavior.
- Ingestion points: The skill reads local files (such as
feasibility-study-*.mdandaudience-study-*.md) and usesWebFetchto ingest remote content from GitHub repositories (READMEs and manifest files). - Boundary markers: There are no instructions to use specific delimiters or to warn the agent to ignore instructions embedded within the ingested data.
- Capability inventory: The agent has capabilities to read and write files in the local environment and perform network operations via
WebSearchandWebFetch. - Sanitization: The procedure does not specify any methods for sanitizing, validating, or filtering the content fetched from external sources before it is processed by the agent.
Audit Metadata