competitor-monitor
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
competitor-tracker.pyusing the${CLAUDE_PLUGIN_ROOT}environment variable to save competitor baseline data to the filesystem. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including competitor websites, social profiles, and ad libraries to synthesize intelligence briefs.
- Ingestion points: Website meta tags, core messaging blocks, social media engagement metrics, and ad copy samples captured during the baseline phase (Step 2).
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to disregard instructions potentially embedded in the scraped competitor content.
- Capability inventory: The skill possesses the ability to perform filesystem writes (via the
competitor-tracker.pyscript) and send data to external notification channels like Slack or Email. - Sanitization: There is no documented process for sanitizing or filtering the ingested external content before it is processed by the agent.
Audit Metadata