content-analytics-engine
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external sources via the PostBridge API, which represents a surface for indirect prompt injection. Maliciously crafted data within social media post captions or other platform metadata could potentially influence the behavior of an AI agent when it processes the generated reports.
- Ingestion points: Data is retrieved from
https://api.post-bridge.com/v1through theanalytics_collector.pyscript, specifically targeting post captions and engagement metrics. - Boundary markers: The skill documentation does not define specific delimiters or "ignore embedded instructions" warnings for the external content it processes.
- Capability inventory: The skill possesses the ability to execute local Python scripts (
report_generator.py) and perform file-write operations to the workspace directory (~/.openclaw/workspace/reports/). - Sanitization: There is no evidence of sanitization, escaping, or validation of the external API data before it is interpolated into the markdown and JSON reports.
Audit Metadata