cco-report

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local utilities report.js and tracker.js using the node runtime via the Bash tool. These operations are used to process internal usage tracking data and provide insights to the user.
  • [INDIRECT_PROMPT_INJECTION]: The agent processes output from reporting tools to generate recommendations, which introduces a data ingestion surface for session logs.
  • Ingestion points: Command output from tracking scripts interpolated into the context of SKILL.md.
  • Boundary markers: Absent; report data is presented to the agent without explicit delimiter isolation.
  • Capability inventory: The skill is limited to Bash and Read tools as defined in the YAML frontmatter.
  • Sanitization: No specific sanitization or filtering logic for tool output is provided in the instruction set.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 05:07 AM