uncomplect
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data including project source code, tests, and runtime receipts, which creates a surface for potential indirect prompt injection.
- Ingestion points: Instructions in SKILL.md command the agent to read project source, tests, runtime receipts, and incidents.
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions within the ingested data are provided in the skill instructions.
- Capability inventory: The skill focus is analytical and does not explicitly request high-privilege tools such as network exfiltration or direct code execution, which limits the potential impact of an injection.
- Sanitization: There is no mention of sanitizing or escaping the external content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill configuration and documentation reference external resources to provide architectural context.
- Details: The 'basis' field in SKILL.md and the 'references/source-map.md' file link to talk transcripts on GitHub, academic materials from Stanford, and official documentation for specialized libraries like Effect and XState. These references target well-known and reputable technology and academic domains.
Audit Metadata