The Agent Skills Directory

[SAFE]: The skill provides structured instructions for interacting with the Harness MCP server to retrieve and manage security data. No malicious commands, exfiltration attempts, or obfuscated payloads were detected.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing external data (vulnerability descriptions, SBOM components) which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: Untrusted data from security scans and SBOMs enters the agent context via the harness_list and harness_get tools as defined in SKILL.md.
Boundary markers: Absent. There are no instructions for the agent to use specific delimiters or ignore instructions embedded within the security data.
Capability inventory: The agent has the capability to modify state (creating and approving exemptions) via harness_create and harness_execute in SKILL.md.
Sanitization: Absent. No explicit sanitization or validation logic is specified for the external content before it is processed by the agent.

security-report