company-hiring-intelligence
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the open web.
- Ingestion points: Data is retrieved from external URLs (careers pages, LinkedIn, and blogs) using the
tinyfish agent runcommand in SKILL.md (Steps 1, 2, and 3). - Boundary markers: Absent. The instructions do not define delimiters or provide specific prompts to ignore malicious instructions embedded within the scraped content.
- Capability inventory: The skill utilizes shell execution (
tinyfishCLI), writes temporary JSON files to/tmp, and accesses the network via the CLI tool. - Sanitization: Absent. The agent is directed to synthesize raw scraped content into a report without intermediate validation or escaping.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@tiny-fish/clipackage from the NPM registry. This is a vendor-specific resource associated with the author 'tinyfish-io'. - [COMMAND_EXECUTION]: The skill frequently executes shell commands (bash, zsh, and PowerShell) to perform environment checks, manage authentication, and orchestrate parallel browser automation tasks.
Audit Metadata