scilla-mode
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data artifacts, which represents a potential surface for indirect prompt injection if those artifacts contain embedded malicious instructions.
- Ingestion points: The skill reads external artifacts including CPU profiles, heap snapshots, traces, and spindumps as defined in
playbooks/runtime-forensics.mdandplaybooks/trace-forensics.md. - Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent instructions.
- Capability inventory: The skill allows for file modifications (bug fixes, log insertion), process instrumentation, and the invocation of other system skills such as
/walkthroughand/build-from-example. - Sanitization: There is no evidence of sanitization or validation performed on the content of the artifacts before processing.
Audit Metadata