generate-doc-description
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes XML files within the
src/main/mule/directory, which constitutes an untrusted data ingestion surface. Malicious instructions could potentially be embedded within the XML comments or data of the target files to influence the agent's behavior during the analysis phase. - Ingestion points: Reads all XML files matching the glob pattern
src/main/mule/**/*.xml. - Boundary markers: No explicit delimiters or instructions are used to isolate the file content from the agent's primary instructions during the analysis phase.
- Capability inventory: The skill utilizes file 'Read' and 'Write' capabilities to modify project source code.
- Sanitization: There is no evidence of sanitization or filtering of the ingested XML content before it is processed by the agent.
Audit Metadata