The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation includes reference links to a domain flagged as malicious by automated reputation scanners.
Evidence: SKILL.md references www.penligent.ai, which is associated with phishing alerts.
Specific URL: https://www.penligent.ai/hackinglabs/virustotal-in-incident-response-how-to-identify-malware-fast-and-pivot-without-leaking-data/.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external threat intelligence sources (VirusTotal API) which includes untrusted content such as community comments and crowdsourced threat names.
Ingestion points: scripts/agent.py and SKILL.md snippets process responses from /files/{hash} and /files/{hash}/behaviours.
Boundary markers: The skill does not implement explicit delimiters or 'ignore' instructions for the data retrieved from the VirusTotal API before displaying it or generating reports.
Capability inventory: The agent has network access via the requests library and the ability to read local files for hashing purposes.
Sanitization: No sanitization or validation of the content returned by the external API is performed before interpolation into the output report structure.

performing-malware-hash-enrichment-with-virustotal