The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external APIs which could contain malicious strings intended to influence agent behavior.
Ingestion points: The skill ingests data via curl requests to VirusTotal, Hybrid Analysis, and MISP endpoints as documented in SKILL.md and references/commands.md.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the fetched intelligence data.
Capability inventory: The skill utilizes curl for network requests, jq for parsing JSON output, and docker for local service orchestration.
Sanitization: No explicit sanitization or validation of the external API responses is performed before processing.
[EXTERNAL_DOWNLOADS]: The skill references several external platforms and repositories for its core functionality.
Fetches threat intelligence data from well-known services including virustotal.com, hybrid-analysis.com, and any.run.
References a community-maintained Docker image for MISP provided by Harvard IT Security for local deployment.

re-ti