The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes requests to https://xquik.com/api/v1, which has been explicitly flagged as a malicious phishing domain by automated security scanners (URLite).
[EXTERNAL_DOWNLOADS]: The SKILL.md file itself was flagged by antivirus software (MD:HttpRequest-inf) as suspicious due to the nature of the network requests it performs to unverified external services.
[DATA_EXFILTRATION]: The skill requires users to provide an API key in the x-api-key header when communicating with xquik.com. Since this domain is flagged for phishing, this behavior constitutes a critical risk for credential harvesting.
[COMMAND_EXECUTION]: The skill provides curl command examples that interact with the flagged malicious domain, demonstrating how an agent would execute potentially dangerous network operations.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted social media content from a third-party API and processes it without security guardrails.
Ingestion points: Public posts are retrieved via the GET /x/tweets/search endpoint as described in the workflow section of SKILL.md.
Boundary markers: The skill does not define any delimiters or system-level instructions to ignore malicious commands embedded within the retrieved social media data.
Capability inventory: The skill allows the agent to perform network requests and process external data, which could be exploited if the fetched data contains malicious instructions.
Sanitization: There is no evidence of sanitization, validation, or filtering of the external API responses before they are integrated into the agent's context.

xquik-social-data