skills/midudev/autoskills/php-pro/Gen Agent Trust Hub

php-pro

Fail

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [METADATA_POISONING]: The skill manifest identifies the author as Jeffallan, which contradicts the expected author context of midudev. The SKILL.md file has also been flagged with a negative file reputation by security scanners.
  • [EXTERNAL_DOWNLOADS]: A documentation link in the skill, https://jeffallan.github.io/claude-skills/skills/language/php-pro/, is blacklisted as malicious according to automated URL reputation scans.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes project source code and configuration files, creating an ingestion point for untrusted data. It lacks specific boundary markers or instructions to mitigate instructions embedded within this data.
  • [COMMAND_EXECUTION]: The skill workflow requires the agent to run command-line tools like phpstan and phpunit against the project files, which could lead to the execution of malicious code contained within those files.
Recommendations
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 17, 2026, 11:21 PM
Security Audit — agent-trust-hub — php-pro