assembly
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing and acting upon external graph data.
- Ingestion points: The skill retrieves untrusted content via tools like iskron_orient, iskron_search, and iskron_look in SKILL.md and references/telos-review.md.
- Boundary markers: No explicit delimiters or instructions are present to prevent the agent from executing commands that might be embedded within node descriptions or inquiry texts.
- Capability inventory: The skill has extensive write access to the graph via iskron_batch, iskron_add_kriya, and iskron_add_bianhua, and can communicate with the owner through iskron_case.
- Sanitization: There is no evidence of content sanitization or validation before the ingested data is used to influence the agent's logic or generate updates to the system.
Audit Metadata