The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions mandate the use of https://brief.day1global.xyz/api/btc-score as the primary data source for all 13 Bitcoin indicators. This URL has been explicitly flagged as malicious (URL:Blacklist) by automated security scanners.
[INDIRECT_PROMPT_INJECTION]: The skill creates a significant attack surface for indirect prompt injection by ingesting and repeating untrusted data from a flagged external API.
Ingestion points: The https://brief.day1global.xyz/api/btc-score endpoint is queried during skill execution to retrieve market metrics, sentiment levels, and action suggestions.
Boundary markers: There are no defined boundary markers or instructions for the agent to treat the API response as potentially untrusted data; the agent is instructed to use the API's suggestion field directly for recommendations.
Capability inventory: The skill uses network access to fetch data and utilizes the agent's text generation capabilities to relay instructions from the remote source.
Sanitization: The skill contains no instructions for sanitizing, validating, or filtering the content received from the remote API before presenting it to the user.
[COMMAND_EXECUTION]: While the skill does not explicitly execute shell commands, the automated file reputation scan flagged SKILL.md as FileRepMalware. The reliance on an external, flagged endpoint for "action recommendations" allows a remote attacker to control the final output and instructions provided by the agent.

btc-bottom-model