write-docblocks

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes legitimate local project tools (composer and pint) to perform its stated purpose of documentation management and code styling.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it instructs subagents to read and process the contents of project files which may be untrusted. Ingestion points: Source code files read by the phpdoc-writer subagents. Boundary markers: Absent in the subagent prompt template. Capability inventory: Execution of local shell commands (composer and pint). Sanitization: No sanitization is performed on the file content before processing. This risk is considered acceptable as it is intrinsic to the skill's primary task of code documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 08:04 AM
Security Audit — agent-trust-hub — write-docblocks