Phy Flag Janitor

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 4:54 AM UTC
• Version: 1.0.3

Overview

Flag Janitor is a local feature-flag auditing guide that reads code, config, .env-style files, and git history to produce cleanup recommendations without external network behavior.

Install only if you are comfortable with the agent reading local source, config files, .env-style feature-flag entries, and git history for the selected project. Review any proposed removals before applying commands, especially changes to production environment examples or flag config.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 115)May include surrounding context.

Environment-variable flags

bash

# From .env files
grep -hE "^[A-Z_]+(_FLAG|_ENABLED|_FEATURE|_TOGGLE)=" .env* 2>/dev/null | \
  cut -d= -f1 | sort -u

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 206)May include surrounding context.

Environment-variable flags

bash

# From .env files
grep -hE "^[A-Z_]+(_FLAG|_ENABLED|_FEATURE|_TOGGLE)=" .env* 2>/dev/null | \
  cut -d= -f1 | sort -u

Credential Access

High

• Category: Privilege Escalation
• Confidence: 60% confidence

Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 363)May include surrounding context.

Environment-variable flags

bash

# From .env files
grep -hE "^[A-Z_]+(_FLAG|_ENABLED|_FEATURE|_TOGGLE)=" .env* 2>/dev/null | \
  cut -d= -f1 | sort -u

Vague Triggers

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The manifest description lists several trigger phrases, including generic phrases like "clean up flags" and "flag cleanup," which are broad enough to match ordinary conversation about feature flags. Because the file does not provide exclusion conditions or negative examples, the activation scope may be wider than intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Low

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

Several trigger phrases are short, generic descriptions of maintenance work rather than precise invocations. Without constraints on context or explicit negative examples, these phrases could unintentionally match routine discussion of flags rather than a deliberate request to run the skill.

Content

No source excerpt is available for this finding.