salary-market-scanner
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external websites, creating a surface for indirect prompt injection attacks.
- Ingestion points: Data is fetched from Levels.fyi, Glassdoor, LinkedIn, and Indeed via the
tinyfish agent runcommand inSKILL.md. - Boundary markers: None are explicitly used to separate the external data from the agent's instructions in the synthesis step.
- Capability inventory: The skill executes shell commands (
tinyfish,cat,echo,npm), writes to temporary files in/tmp, and performs network operations via sub-agents. - Sanitization: No sanitization or validation of the scraped content is performed before it is used to generate the final report.
- [COMMAND_EXECUTION]: The skill uses shell commands to verify the environment, authenticate with the vendor platform, and execute scraping tasks using the
tinyfishCLI tool. - [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@tiny-fish/clipackage from the npm registry and connects to various well-known job boards and salary databases to retrieve data.
Audit Metadata