word-count-checker
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'wc' command-line utility via Bash to perform word counts on local files.- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to command injection because it directly interpolates user-provided filenames into a shell command without sanitization. An attacker could provide a filename containing shell metacharacters to execute unauthorized commands. Ingestion points: Target filenames are identified directly from user messages as described in SKILL.md. Boundary markers: None present to distinguish data from instructions. Capability inventory: Execution of shell commands ('wc -w') is enabled across the skill's workflow. Sanitization: No input validation, escaping, or filtering of the filename variable is implemented.
Audit Metadata