social-listening
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to extract API credentials from a local file. Specifically, it uses
python3 -cto parse the~/.gooseworks/credentials.jsonfile to set environment variables for the API key and base URL. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from the web and social media for further analysis.
- Ingestion points: Data is retrieved from social media platforms (X/Twitter, LinkedIn) via Scrape Creators and broad web mentions via Exa. Additionally, Scrapegraph is used to extract text and structured data from arbitrary website URLs.
- Boundary markers: The skill instructions do not provide delimiters or specialized formatting to isolate retrieved external content from the agent's primary instructions.
- Capability inventory: The skill possesses the capability to perform network requests (via
curl) and read specific local configuration files (viapython3). - Sanitization: No sanitization, filtering, or safety-aware parsing of retrieved external content is specified before the data is processed by the agent to extract sentiment or insights.
Audit Metadata