cco-roi
Warn
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Node.js script ('roi.js') using the Bash tool. The instruction 'node ${CLAUDE_PLUGIN_ROOT}/src/roi.js $ARGUMENTS' includes unquoted user-supplied arguments, which is a pattern vulnerable to shell command injection if metacharacters such as semicolons, pipes, or ampersands are included in the user input.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to generate a report, creating an attack surface for indirect prompt injection.
- Ingestion points: User-supplied '$ARGUMENTS' entering the agent context via SKILL.md.
- Boundary markers: Absent; there are no delimiters or 'ignore' instructions for the interpolated user data.
- Capability inventory: The skill has the ability to execute shell commands via the 'Bash' tool as specified in SKILL.md.
- Sanitization: Absent; the instructions do not describe any validation, escaping, or filtering of the external content.
Audit Metadata