The Agent Skills Directory

[SAFE]: The skill provides legitimate coding guidelines and incorporates security best practices such as dependency auditing and static analysis. No malicious patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill outlines the development of services that ingest data from databases and external APIs, which represents a potential attack surface for indirect prompt injection if the resulting agent processes untrusted input without proper boundaries.
Ingestion points: Database reads and external API calls are described in SKILL.md (Capabilities section 3 and 5).
Boundary markers: Absent. No specific prompt delimiters or instructions to ignore embedded commands are provided for handling external data.
Capability inventory: SKILL.md suggests using tools like Rector and Pint which perform file system writes.
Sanitization: Present. The skill mandates strict_types=1, high-level static analysis (PHPStan/Psalm Level 9), and the use of security auditing tools (composer audit, roave/security-advisories) to improve code quality and safety.

performant-php