braun-poke-the-bear
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected. The skill is purely informational.
- [NO_CODE]: The skill does not include any executable scripts (.py, .js, .sh), binaries, or configuration files that trigger command execution.
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs in
DERIVATION.jsonandreferences/sources.mdfor documentation and educational purposes related to the sales method. These links (targeting joshbraun.com and linkedin.com) are intended for human or agent reference and do not involve automated execution of remote code. - [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for processing user-supplied data regarding sales prospects to generate outreach drafts.
- Ingestion points: User input is used to fill fields in
templates/output-template.md(e.g., Prospect and job, Seller identity). - Boundary markers: The skill does not define specific delimiters for untrusted input.
- Capability inventory: The skill possesses no executable capabilities; it is limited to text generation within the agent's context.
- Sanitization: No specific sanitization or filtering of user-supplied data is implemented, relying on the model's standard output filters.
Audit Metadata