stalk-my-interviewer
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to check for the TinyFish CLI, manage authentication, and run parallel research agents that store results in temporary files within
/tmp. - [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@tiny-fish/clipackage from the NPM registry, which is the official tool provided by the vendor for this skill's functionality. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data from LinkedIn, GitHub, X, and Google Search. 1. Ingestion points: Data is pulled from external user profiles and search result snippets via
tinyfish agent runcommands in SKILL.md. 2. Boundary markers: There are no explicit delimiters or instructions to ignore instructions found within the scraped data during the Step 3 synthesis. 3. Capability inventory: The agent has access to shell command execution through the TinyFish CLI. 4. Sanitization: The skill does not implement validation or escaping for the scraped external content before it is processed by the AI.
Audit Metadata