The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill documentation specifies a remote API at http://88.222.241.169 for data retrieval. The use of unencrypted HTTP for transmitting Bearer tokens presents a risk of credential exposure during transit.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted text from external sources, specifically AI-generated summaries of Feishu group chats and KOL opinions. Malicious instructions embedded in these summaries could potentially manipulate the agent's behavior. \n- Ingestion points: Content is retrieved via API endpoints like /api/v1/summaries and /api/v1/second_kol as described in SKILL.md. \n- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within the fetched data. \n- Capability inventory: The agent is empowered to fetch, summarize, and present market data and social sentiment. \n- Sanitization: There is no description of content filtering or sanitization being performed on the data retrieved from the remote API.

erwa-api