axiom-audit-resize
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of project source code (.swift) and configuration files (.plist) using standard file system tools like Glob, Grep, and Read.
- Ingestion points: Project files identified via
Glob: **/Info.plist, **/*.swiftand subsequentGrepandReadoperations. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or explicit system-level instructions to ignore embedded prompts within the audited content.
- Capability inventory: The skill utilizes file system exploration and read capabilities to analyze code structure, configuration keys, and logic patterns.
- Sanitization: No explicit sanitization or filtering of the content read from files is described, which could allow an attacker to embed instructions within code comments or string literals that attempt to influence the agent's behavior during the audit process.
Audit Metadata