nestr-basics
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a Nestr workspace which acts as an untrusted ingestion point for external content.
- Ingestion points: Data is pulled into the agent's context through commands like
nestr search,nestr nests get,nestr comments list, andnestr notifications list(SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded within the retrieved workspace data.
- Capability inventory: The skill allows the agent to modify the workspace state using
nestr nests create,nestr nests update,nestr nests delete, andnestr comments add(SKILL.md). - Sanitization: There is no evidence of sanitization or validation of the content retrieved from the workspace before it is processed by the agent.
Audit Metadata