teach-pstack
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including source code, git diffs, and debugger output, to provide explanations to the user.
- Ingestion points: The skill reads user-provided codebases, diffs, and debugger state as specified in the execution steps (e.g., Step 2 and Step 5).
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from obeying malicious instructions that might be embedded within the code or diffs being analyzed.
- Capability inventory: The skill possesses the ability to invoke other internal skills (how, why, unslop), read local files, and use an image-generation tool.
- Sanitization: The instructions do not define any sanitization, filtering, or escaping mechanisms for the external content before it is processed or passed to other tools.
Audit Metadata