T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:173- Finding
Shell Command Injection Through Unquoted Git Branch Names
- Content
View full analysis
- Remediation
View remediation
Security audit
Phy Git Branch Janitor
Security checks for vulnerabilities and agentic risk
Overview
The skill fits its Git branch-cleanup purpose, but it needs review because it can generate copy-paste delete commands that are unsafe for unusual branch names.
Review generated commands before running them, especially in repositories with branches created by other people. Do not paste cleanup commands blindly; branch names should be validated and shell-quoted, and remote deletions or force-deletes should be confirmed manually.
Vulnerability Patterns
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The description advertises triggers such as "clean up branches," "stale branches," and especially "delete old branches," which are fairly broad natural-language phrases and could overlap with ordinary conversation about Git maintenance. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
Several listed triggers, including "branch cleanup," "stale branches," and "which branches can I delete," are understandable but still broad enough to match common repo discussions rather than an intentional skill invocation. The section does not define required context, exclusions, or a canonical invocation format beyond one slash-command option.
- Content