netsec-health
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script at
.claude/hooks/netsec-health.shto perform its primary function of verifying the security environment. - [PRIVILEGE_ESCALATION]: The instructions direct the agent to ensure hook scripts are executable, potentially using
chmod +x. This is a standard administrative task for managing local security scripts. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and interprets the output of the health check script, which represents an entry point for external data into the agent's context.
- Ingestion points: Output from the execution of
bash .claude/hooks/netsec-health.sh. - Boundary markers: No explicit delimiters are defined to separate script output from subsequent agent instructions.
- Capability inventory: The skill utilizes shell command execution and file permission modification.
- Sanitization: There are no instructions for sanitizing or validating the script output before it is processed by the agent.
Audit Metadata