The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to read and parse local credential files using Python.
Evidence: export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])") in SKILL.md.
[DATA_EXFIL_TRATION]: The skill performs network requests to the Gooseworks API and has capabilities to extract sensitive session cookies.
Evidence: usage of curl commands targeting api.gooseworks.ai and the Get Session Cookies capability described in SKILL.md.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its web scraping capabilities.
Ingestion points: The Scrape Webpage, Observe Page, Scrape from HTML, and Scrape Page endpoints in SKILL.md allow the agent to ingest content from untrusted external websites.
Boundary markers: The skill does not define specific delimiters or include instructions to the agent to ignore potentially malicious commands embedded in the scraped data.
Capability inventory: The skill possesses high-risk capabilities, including Execute Page Action, Set Session Cookies, Get Session Cookies, and Start Agent.
Sanitization: No sanitization or validation logic is mentioned for the content retrieved from external sources before it is processed by the AI agent.

browser-automation-notte