Security audit

git-commit-summarizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent local Git commit summarizer, with a limited output-escaping weakness but no evidence of hidden access, persistence, network use, or destructive behavior.

Reasonable to install for local commit summaries. Be cautious using its JSON output in automated pipelines or on untrusted repositories until JSON escaping and terminal-control sanitization are improved.

A.I.G

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)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/summarize.sh:47
Finding: Unescaped Repository-Controlled Data in JSON and Terminal Output
Content: View full analysis
Remediation: View remediation
&2; exit 1 ;; esac ``` 4. Sanitize terminal-oriented output by removing or visibly encoding non-printable control characters before printing repository-controlled author names or commit subjects. 5. Use `printf '%s\n'` instead of `echo` for untrusted values to avoid implementation-dependent handling of escape-like input. 6. Add regression tests covering commit subjects, author names, and arguments containing: - Double quotes - Backslashes - The `|` delimiter - Tabs and control characters - JSON-like fragments - Unicode characters 7. Verify generated JSON with a strict parser as part of automated testing. ]]>

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.