gsd-quick
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Detected a vulnerability surface for indirect prompt injection. 1. Ingestion points: The skill ingests untrusted data via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: There are no delimiters or instructions to ignore embedded commands within the argument interpolation. 3. Capability inventory: The skill has access to powerful tools including Bash, Write, Edit, and Task (SKILL.md), which could be misused if malicious instructions are injected via arguments. 4. Sanitization: The configuration does not define any sanitization or validation for the input data.
Audit Metadata