teach-pstack
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and explain external "bodies of work" (code, subsystems, or git changes), which creates an inherent surface for indirect prompt injection attacks if the content contains adversarial instructions.
- Ingestion points: The skill explicitly instructs the agent to "Read the code yourself to get oriented" as seen in
SKILL.md. - Boundary markers: There are no specific instructions or delimiters provided to the agent to treat external content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill possesses the ability to invoke other skills (
how,why,unslop), use Mermaid diagramming, and access an image-generation tool. - Sanitization: The instructions lack guidance on sanitizing, escaping, or validating external content before it is processed or used in the final explanation.
Audit Metadata