openhound-jamf
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing external JamfHound data snapshots and methodology documents which could contain untrusted content.
- Ingestion points: The workflow explicitly directs the agent to read external JSON snapshots and markdown methodology files located in parent directories (e.g.,
../../references/docs/). - Boundary markers: There are no instructions provided to treat the external data as untrusted or to use specific delimiters to separate data from instructions.
- Capability inventory: The skill is designed to generate Cypher queries and perform attack-path triage, often interfacing with the
$bloodhound-querytool. - Sanitization: The skill does not prescribe any validation or sanitization steps for the ingested JSON data or documentation.
- [NO_CODE]: The skill contains markdown instructions, metadata, and an icon, but does not include any executable scripts, binaries, or active code components within the skill package itself.
Audit Metadata