The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and correlate data from a wide variety of external, untrusted sources including web search results, website content, and public API responses.
Ingestion points: Data enters the agent's context through WebSearch, WebFetch, and the output of curl commands directed at external services like crt.sh (as seen in SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded in the OSINT data it collects.
Capability inventory: The skill utilizes Bash (permitting shell commands like dig and whois), WebFetch, and Write capabilities.
Sanitization: The skill does not define any sanitization, filtering, or validation logic for the content retrieved from external sources before it is analyzed or reported.
[EXTERNAL_DOWNLOADS]: The skill uses curl to fetch data from crt.sh to identify subdomains. This is a neutral, informative finding as crt.sh is a well-known service for certificate transparency logs and is used here for its intended purpose.

osint-recon