hunter-scout
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to multiple well-known job board platforms (Greenhouse, Lever, Ashby, Workday, and Eightfold) to fetch live job listings. These network operations are core to the skill's documented functionality and target official public APIs.
- [DATA_EXPOSURE]: The skill reads the user's profile (
hunter/profile.json) to perform local scoring of job listings. When performing searches on Workday or Eightfold boards, it sends the user's target job titles as search query parameters. This is a standard and necessary behavior for the intended purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill ingests job descriptions from external sources which could theoretically contain malicious instructions. To mitigate this risk, the skill implements a sanitization function (
html_text) injobs.pythat strips HTML tags, scripts, and style blocks before the content is processed or displayed to the agent. - Ingestion points: Job descriptions are fetched from external board APIs in
jobs.pyvia theFetcher.getmethod. - Boundary markers: Job listings are presented in a structured list format, though they do not use specific security-oriented delimiters for the description text.
- Capability inventory: The skill has the capability to write to local files (
hunter/jobs.json,hunter/pipeline.json) and perform HTTP GET/POST requests. - Sanitization: The
html_textutility removes executable HTML elements and scripts from the ingested text.
Audit Metadata