php-injection-audit
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external evidence markers (EVID_*) from an automated tool (php-audit-pipeline). This presents a theoretical surface for indirect prompt injection if an attacker can manipulate the audited source code to include malicious instructions that are subsequently extracted as evidence.
- Ingestion points: Evidence data generated from php-audit-pipeline as described in SKILL.md.
- Boundary markers: None explicitly defined to separate instructions from external evidence data.
- Capability inventory: No executable capabilities such as file system writing, network requests, or shell command execution are defined within the skill instructions.
- Sanitization: No validation or sanitization logic for the ingested data is present.
- [SAFE]: The skill consists of markdown-based instructions, checklists, and code examples for security auditing. No patterns of credential theft, remote code execution, or persistence were detected. All code snippets provided are for reference and are not executed by the skill.
Audit Metadata