setup-pstack
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages configuration data that influences agent behavior in subsequent sessions. It includes validation logic to ensure only detected or valid alias model slugs are written to the configuration files, mitigating the risk of injecting invalid or malicious model identifiers.\n
- Ingestion points: Reads existing settings from
~/.cursor/rules/pstack-models.mdc,~/.claude/rules/pstack-models.md, and~/.agents/pstack-models.md.\n - Boundary markers: Absent; the configuration is stored as plain text/markdown rules.\n
- Capability inventory: Performs file read and write operations to the specified configuration paths and executes harness-specific commands to list available models.\n
- Sanitization: Implements a validation step to ensure all written model slugs are confirmed as available in the current environment.
Audit Metadata