skills/jeremylongshore/tons-of-skills-marketplace/salesforce-advanced-troubleshooting/Gen Agent Trust Hub
salesforce-advanced-troubleshooting
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data originating from a Salesforce organization, including debug logs and Apex code, which could potentially contain malicious instructions.
- Ingestion points: The skill downloads logs via 'sf apex log get' and queries 'ApexTrigger' bodies and 'EventLogFile' data in 'SKILL.md'.
- Boundary markers: No explicit delimiters or instructions are provided to ensure the agent ignores instructions embedded within the fetched data.
- Capability inventory: The skill uses 'Bash(sf:)', 'Bash(curl:)', and 'Read' tools to interact with the environment.
- Sanitization: No validation or sanitization of the downloaded Salesforce data is performed before analysis.
Audit Metadata