php-csrf-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core function is to ingest and analyze untrusted PHP source code and execution trace data from external projects. This inherent behavior creates a surface for indirect prompt injection, where malicious payloads embedded in the audited code could attempt to manipulate the agent's logic.
- Ingestion points: The agent is instructed to read PHP project source code and trace data provided by
php-route-tracer. - Boundary markers: The instructions do not establish explicit boundary markers or "ignore instructions" delimiters to isolate the audited code from the agent's execution context.
- Capability inventory: The skill facilitates the creation of detailed vulnerability reports and Proof-of-Concept (PoC) exploits, which are written to a local output path.
- Sanitization: There are no specified requirements for sanitizing, escaping, or validating the content extracted from audited files before it is included in the output reports.
Audit Metadata