The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands for verification and configuration, specifically curl, jq, grep, and the isagentready CLI tool.
[PRIVILEGE_ESCALATION]: To obtain and install SSL certificates, the skill directs the agent to use sudo certbot, which involves gaining administrative permissions.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data via the $ARGUMENTS variable, which is then used to define target domains or checkpoint IDs in shell commands without sanitization.
Ingestion points: User-provided domain or checkpoint ID via $ARGUMENTS in SKILL.md.
Boundary markers: The instructions lack delimiters or explicit warnings to ignore potential instructions embedded within the user-provided domain string.
Capability inventory: The skill employs curl, grep, jq, sudo certbot, and the isagentready CLI across its workflows.
Sanitization: There is no logic provided to validate or sanitize the $ARGUMENTS input before it is interpolated into command-line strings.
[EXTERNAL_DOWNLOADS]: The skill relies on the isagentready CLI tool and references methodology and scoring data hosted on isagentready.com, which is a third-party service not categorized as a well-known or trusted provider.

security-trust