freelance-gig-finder

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the @tiny-fish/cli package from the npm registry. This package is an official resource provided by the skill vendor, tinyfish-io, to facilitate its job-searching features.
  • [COMMAND_EXECUTION]: The skill uses several shell commands to manage its workflow, including verifying CLI installation using which, checking authentication status via tinyfish auth status, and running search agents that pipe results to JSON files in the /tmp directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external job boards including Upwork, LinkedIn, and Freelancer. While this data is sourced externally, the risk is mitigated by the use of constrained prompts for data extraction.
  • Ingestion points: Data is pulled from multiple external job search URLs into the skill workflow via the tinyfish agent run command in SKILL.md.
  • Boundary markers: The prompts used for data extraction contain strict rules that limit the agent to visible content and specific JSON structures.
  • Capability inventory: The skill has the ability to execute shell commands and read/write to temporary files.
  • Sanitization: The skill employs structured prompting to ensure external content is parsed into predefined fields before being displayed to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 01:04 AM