ck-help
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
.claude/scripts/ck-help.pyusing user-provided arguments passed as a string. This execution is used to retrieve structured help and documentation content. - [PROMPT_INJECTION]: The skill processes and presents the full output of an internal script without sanitization, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested from the output of the local helper script
.claude/scripts/ck-help.py(SKILL.md). - Boundary markers: The instructions do not define boundary markers or delimiters for the script's output, requiring the agent to show it verbatim.
- Capability inventory: The skill has the capability to execute local Python scripts and perform task management via the
TaskCreatetool (SKILL.md). - Sanitization: There is no explicit sanitization, validation, or escaping of the script output before it is presented to the user or incorporated into the agent's context.
Audit Metadata