squad-fix
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating a surface for indirect prompt injection.
- Ingestion points: The skill processes 'issue text, logs, traces, payloads, screenshots, external docs, and generated output' as specified in
SKILL.md. - Boundary markers:
SKILL.mdincludes instructions to 'Redact secrets and personal data' and defines clear scopes for different roles, though it lacks formal delimiters for untrusted input. - Capability inventory: The skill possesses significant capabilities including file modification ('Implementation' step in
SKILL.md) and command execution for verification ('Verify' step inSKILL.md). - Sanitization: The skill mandates manual redaction of sensitive information and requires 'explicit authority and required recovery controls' before mutating production environments or external services.
Audit Metadata