blooming-blockery-cli
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Analysis of indirect prompt injection vulnerability surface as defined in Category 8.
- Ingestion points: The agent ingests potentially untrusted data through commands such as
bb show,bb context,bb find, andbb mount expandas documented inSKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data content and system instructions when processing block content.
- Capability inventory: The skill documents powerful capabilities including file system writes (
bb mount save,bb mount extract), content modification (bb point), and data deletion (bb tree delete). - Sanitization: The documentation does not mention any sanitization, escaping, or validation mechanisms for the text content being processed or rendered.
Audit Metadata