axiom-audit-camera
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on providing developer guidance and auditing local Swift source code for specific capture-related patterns. No malicious commands, obfuscation, or data exfiltration attempts were detected.\n- [PROMPT_INJECTION]: The skill processes untrusted input in the form of project source code, creating a surface for indirect prompt injection (Category 8). However, because the skill is restricted to textual analysis and lacks high-risk capabilities like network access or file writing, the risk is negligible and does not warrant a non-safe verdict.\n
- Ingestion points: The skill scans all Swift files (
**/*.swift) within the user's project as specified in the SKILL.md instructions.\n - Boundary markers: There are no explicit delimiters used when the agent reads the code, nor are there instructions to ignore potential command-like directives found within the audited files.\n
- Capability inventory: The skill is configured to provide an audit report. It does not contain instructions to utilize tools for network communication or local system modifications.\n
- Sanitization: The skill does not perform any sanitization or filtering of the code content it analyzes.
Audit Metadata