platform-apex-test-generate
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the project environment which could be used to influence agent behavior.
- Ingestion points: In SKILL.md, the agent reads 'target production class(es)', 'existing test classes', and 'coverage reports' (Step 1), as well as 'failing methods — exception types and stack traces' (Step 4).
- Boundary markers: Absent. The skill does not instruct the agent to use specific delimiters or to ignore instructions embedded within the source code or test output it reads.
- Capability inventory: The skill executes shell commands via the
sfCLI (Step 3) and writes multiple Apex and XML files to the local filesystem (Step 2 and assets/ templates). - Sanitization: Absent. There are no procedures defined to sanitize or validate the content of the files or reports before they are interpolated into prompts or used to construct CLI arguments.
Audit Metadata