skills/jeremylongshore/tons-of-skills-marketplace/building-recommendation-systems/Gen Agent Trust Hub
building-recommendation-systems
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as user interaction logs and item features, to generate executable Python code. This represents an indirect prompt injection surface where malicious instructions could be embedded in the data to influence the agent's code generation.
- Ingestion points: Interaction data, user preferences, and item features described in
SKILL.mdand configured inassets/configuration_template.yaml. - Boundary markers: The skill lacks explicit instructions or delimiters to isolate processed data from the agent's instruction context.
- Capability inventory: The skill defines access to
Bash(cmd:*),Read,Write, andEdittools inSKILL.md. - Sanitization: No data validation or sanitization mechanisms are described or implemented for the ingested datasets.
- [SAFE]: The configuration template in
assets/configuration_template.yamlfollows security best practices by using descriptive placeholders for sensitive credentials, such asYOUR_DATABASE_PASSWORD, rather than hardcoded secrets.
Audit Metadata