resolve-company-domain
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites to validate domain ownership, which creates a potential surface for instructions embedded in those sites to influence the agent.
- Ingestion points: Homepage
bodyText,title, and metadata tags (canonical,og:url) are processed inreferences/validation-ladder.md(Step 2 and 3). - Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands within the scraped content.
- Capability inventory: The agent utilizes the
clayCLI and has file system access for reading and writing answer sheets (mentioned inSKILL.md). - Sanitization: No sanitization or filtering of the scraped content is documented before it is semantically analyzed by the agent.
- [COMMAND_EXECUTION]: The skill directs the agent to execute specific shell commands to verify and interact with the Clay environment.
- Evidence: Instructions in
SKILL.md(Step 0) require runningclay whoami,clay routines list, andclay routines get <id>.
Audit Metadata