company-recon
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and synthesizes untrusted data from external websites via
web_fetchandweb_searchtools. This creates an attack surface where a target website containing malicious prompt injection instructions could potentially override agent behavior or influence the generated report. - Ingestion points: Content retrieved from user-provided company URLs and web search results (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to isolate external web content from the agent's core instructions.
- Capability inventory: The agent has the capability to create and save files in
.docxand HTML formats. - Sanitization: The instructions do not require sanitization or validation of the fetched external content before it is used for synthesis.
Audit Metadata