modern-drug-rehab-computer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by combining untrusted data ingestion with exploitable file-system capabilities. * Ingestion points: The skill is configured to use 'WebFetch' and 'WebSearch' tools to retrieve external content. * Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded in retrieved data. * Capability inventory: The skill allows the use of 'Write' and 'Edit' tools, which could be leveraged to modify the local environment if the agent is manipulated by external data. * Sanitization: The instructions do not include any protocols for validating or sanitizing data fetched from the web before processing or storage.
- [NO_CODE]: Technical analysis confirms that the skill is composed entirely of informational Markdown documentation and references, containing no executable scripts, binaries, or external software dependencies.
Audit Metadata