page-copy
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files which could potentially harbor malicious instructions intended to hijack the agent's behavior during the copy-writing process.
- Ingestion points: The skill reads data from
workspace/pages/[page-name]/strategy.json,workspace/brand/profile.md, andworkspace/brand/extract.mdas specified in the 'Required inputs' section ofSKILL.md. - Boundary markers: There are no explicit boundary markers or 'ignore' instructions provided to the agent to differentiate between the data in the ingested files and the core instructions.
- Capability inventory: The skill's functionality is limited to text generation; analysis of
SKILL.mdreveals no subprocess executions, file system write operations, or network communication capabilities. - Sanitization: The skill does not implement validation or sanitization of the content extracted from the input files before processing.
- [NO_CODE]: The skill consists entirely of instructional markdown and configuration metadata with no accompanying scripts or executable binaries, significantly limiting its attack surface.
Audit Metadata