The Agent Skills Directory

[SAFE]: No malicious patterns, persistence mechanisms, or credential theft attempts were detected. The skill's operations are transparent and consistent with its stated purpose of researching person backgrounds.
[COMMAND_EXECUTION]: The skill uses the orth run command to invoke external APIs. It correctly encapsulates search parameters within JSON payloads to prevent command injection vulnerabilities.
[PROMPT_INJECTION]: The skill ingests data from external person-research services, creating an indirect prompt injection surface as outlined in Category 8.
Ingestion points: Results from API calls to the nyne and fiber tools as defined in SKILL.md.
Boundary markers: Absent; external data is presented directly to the agent's context.
Capability inventory: Shell command execution via orth run (SKILL.md).
Sanitization: No explicit validation or filtering of the retrieved profile data is specified.

person-lookup