The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's core functionality involves running shell commands, referred to as 'safe checks', to verify that specific requirements or completion conditions have been met. It requires recording the command, exit status, and output as evidence in a verification report.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its fact-checking feature.
Ingestion points: The skill ingests untrusted data from user-provided text, external documentation, and primary sources via the --text flag and repository file inspection.
Boundary markers: There are no explicit instructions for using delimiters or boundary markers to isolate processed text from the agent's instructions.
Capability inventory: The agent can execute shell commands ('safe checks') and read repository files as described in SKILL.md.
Sanitization: The instructions do not specify any sanitization, filtering, or escaping of the external content before it is processed by the agent.

hl-verify