attio-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches official documentation from Attio's developer portal to maintain up-to-date API contracts.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files and external documentation, creating an attack surface for indirect prompt injection.
- Ingestion points: Project files accessed via
Read,Glob, andGrep, and external documentation viaWebFetchinSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the agent to use when processing external data.
- Capability inventory: The skill is authorized to perform file system modifications using the
WriteandEdittools. - Sanitization: Instructions require the use of sanitized fixtures and synthetic values, which reduces data leakage risks but does not eliminate the risk of the agent obeying instructions embedded in the data it reads.
Audit Metadata