astrology-interpretation-guide
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions in
modules/research-checklist.mdestablish a workflow for indirect prompt injection by directing the agent to ingest untrusted data from external sources. - Ingestion points: External data enters the agent context through web searches, Wikipedia distillation (
distill_from_wikipedia), and ArXiv distillation (distill_from_arxiv) as described inmodules/research-checklist.md. - Boundary markers: The skill does not define explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within the retrieved research data.
- Capability inventory: No scripts or tool execution capabilities (such as subprocess calls, file writes, or network operations) are present within the skill files themselves.
- Sanitization: There are no mechanisms described for sanitizing or validating the content fetched from external providers before it is incorporated into the agent's knowledge base.
Audit Metadata