salesforce-data-handling
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates repository and evidence files to assess data classification, which creates a surface where external data could potentially contain instructions that influence the agent's behavior.
- Ingestion points: External repository and evidence files accessed via
Read,Glob, andGreptools. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore commands potentially embedded within the data sources.
- Capability inventory: The skill allows the use of
Write,Edit, andWebFetchtools to generate plans and reference documentation. - Sanitization: No explicit process for sanitizing or filtering the content of ingested files for prompt injection patterns is mentioned.
Audit Metadata