The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill instructions direct the agent to read sensitive API credentials from the local filesystem at ~/.gooseworks/credentials.json using shell commands (python3 -c). These credentials are then stored in environment variables and used for subsequent network requests.
[EXTERNAL_DOWNLOADS]: The setup instructions include the command npx gooseworks login, which downloads and executes code from the npm registry at runtime.
[COMMAND_EXECUTION]: The skill makes extensive use of curl to interact with external API endpoints at api.gooseworks.ai to perform searches and scraping operations.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from various external sources:
Ingestion points: Data is fetched from the public web via Exa, and from social media platforms (X/Twitter, LinkedIn) via Scrape Creators and Scrapegraph.
Boundary markers: The instructions do not define any delimiters or provide guidance to the agent to ignore or isolate potentially malicious instructions embedded in the scraped web content.
Capability inventory: The agent has the capability to execute shell commands (curl, python3) and perform network operations.
Sanitization: There is no evidence of sanitization, filtering, or validation performed on the external data before it is processed by the agent.

social-listening