iotech-expert
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local shell script (
scripts/sync-docs.sh) to verify the freshness of its reference documentation and perform updates. The script uses standard system utilities includingcurl,pandoc, andpython3for file management and content transformation. - [EXTERNAL_DOWNLOADS]: The maintenance script performs network requests to
docs.iotechsys.comto download updated documentation. These downloads originate from the official vendor domain associated with the skill's primary purpose. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing data from an external website (
docs.iotechsys.com). The ingestion process includes documented evidence: - Ingestion points: The
scripts/sync-docs.shscript fetches content from remote URLs defined in.url-map.json. - Boundary markers: The script wraps ingested content with markdown comment headers indicating source URLs and synchronization dates.
- Capability inventory: The skill possesses the capability to execute shell commands, perform network operations, and modify its own reference directory.
- Sanitization: External HTML content is converted to markdown using the
pandocutility before being presented to the agent.
Audit Metadata