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 -c to parse the ~/.gooseworks/credentials.json file 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 (via python3).
  • 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
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:14 PM
Security Audit — agent-trust-hub — social-listening