audit-augmentation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or safety bypass attempts were detected. The skill provides legitimate functionality for security auditors to project tool findings onto code structure for reachability analysis.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'trailmark' CLI and library via
uv. This is a vendor-owned resource provided by the author ('trailofbits') and is the primary tool for this skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (SARIF, weAudit, and binary graphs), which represents a surface for indirect prompt injection or schema confusion.\n - Ingestion points: Data enters the engine via
augment_sarif,augment_weaudit, andaugment_binarycalls as described in the programmatic API section ofSKILL.md.\n - Boundary markers: The skill processes findings as structured data (JSON/SARIF) and creates graph annotations, which provides structural isolation from the agent's primary instructions.\n
- Capability inventory: Ingested data is used to create subgraphs and annotations for querying (
engine.findings(),engine.subgraph()); there are no high-risk capabilities like network exfiltration or arbitrary command execution driven by the ingested content.\n - Sanitization: The skill relies on the underlying 'trailmark' engine to parse and validate the specific security data schemas.
Audit Metadata