hunt-sharepoint
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains multiple shell commands using tools like curl, jq, and grep to perform reconnaissance on remote servers. These commands facilitate tasks such as version fingerprinting and endpoint probing, which are intended for use in authorized security assessments.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process data from external SharePoint endpoints. Ingestion points: Data is received from external servers via curl commands in SKILL.md (Steps 1, 2, 4, 6, 8, 9). Boundary markers: The skill implements a 'Mandatory confirmation gate' requiring the user to explicitly confirm targets and authorization. Capability inventory: Commands include network requests (curl) and local processing (jq, grep, python3). Sanitization: Uses structured parsing with jq and pattern matching with grep to interpret target responses.
Audit Metadata