registry / philset / 0.3.0

philset@0.3.0

Claude Code skills library for iterative, document-driven development

AI Security Review

scanned 3h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

User runs philset init, begin/dsp/private, update, or sync.

Impact

Can alter Claude Code behavior and local project metadata; --dsp can cause Claude to operate without normal permission prompts.

Mechanism

User-invoked AI-agent skill/config deployment and optional unsafe Claude launch.

Rationale

No malicious install-time or exfiltration chain was found, but the package deliberately mutates Claude Code control surfaces and offers an unsafe execution mode when invoked. This meets the warning threshold for explicit user-command AI-agent capability abuse.

Evidence

package.jsonbin/philset.jstemplates/CLAUDE.mdskills/hello/skill.md~/.claude/skills<cwd>/.meta<cwd>/CLAUDE.md<git-root>/.git/info/exclude

Decision evidence

public snapshot

AI called this Suspicious at 93.0% confidence as Dangerous Capability with low false-positive risk.

philset@0.3.0

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code