The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The script scripts/crypto.py performs network requests to api.coingecko.com. While this is the intended purpose of the skill, the domain is not included in the predefined trusted whitelist.
[PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection because it processes data from an external API.
Ingestion points: Market data is fetched from the CoinGecko API in scripts/crypto.py and returned to the agent.
Boundary markers: Absent. SKILL.md does not specify delimiters or instructions for the agent to ignore instructions embedded in the API response.
Capability inventory: The skill executes a Python script via subprocess (python3 scripts/crypto.py <symbol>) but does not perform file-write or network-send operations based on the ingested data.
Sanitization: The script uses json.loads to ensure the response is valid JSON, though it does not sanitize the content of the strings returned by the API.
[COMMAND_EXECUTION] (SAFE): The skill executes a local script using arguments derived from user input. The script handles these arguments within Python and does not utilize a shell (shell=True) or dangerous execution functions like eval().

crypto