company-deep-dive
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a significant attack surface for indirect prompt injection as its primary function is to ingest and process data from external, untrusted web sources.
- Ingestion points: In
SKILL.md, Step 1 ('Research five dimensions in parallel') and Step 2 ('Extract the pages that matter') involve performing web searches and extracting full text from arbitrary external URLs. - Boundary markers: Absent. The instructions do not direct the agent to wrap external content in specific delimiters or use defensive prompts to ignore embedded instructions within the fetched data.
- Capability inventory: The skill has the capability to read from and write to the local workspace environment, specifically managing files in the
memory/directory as described inreferences/company-memory.md. - Sanitization: Absent. There are no instructions for the agent to sanitize, filter, or validate the content retrieved from the web before it is integrated into the agent's context or written to memory files.
Audit Metadata