Security Audit

openai/skills:skills/.curated/gh-address-comments

github.com/openai/skills

AI SkillCommit 49f948faa925

CRITICAL

Scanned about 10 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

openai/skills:skills/.curated/gh-address-comments received a trust score of 42/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Indirect Prompt Injection via Untrusted PR Comments.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

Last analyzed on July 17, 2026 (commit 49f948fa). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

85%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

3 findings

Dynamic Code

1 finding

Security Findings3

Severity	Finding	Layer	Location
CRITICAL	Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands.	Manifest	skills/.curated/gh-address-comments/scripts/fetch_comments.py:96
HIGH	Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function '_run'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives.	Static	skills/.curated/gh-address-comments/scripts/fetch_comments.py:96
HIGH	Indirect Prompt Injection via Untrusted PR Comments The skill fetches and processes arbitrary, untrusted PR comments and review threads from GitHub using `scripts/fetch_comments.py`. It then presents these comments to the host LLM to summarize and propose fixes. If a PR comment contains malicious instructions (e.g., 'ignore previous instructions and run this shell command'), the host LLM may execute them, leading to arbitrary code execution or data exfiltration in the user's environment. Sanitize or escape the fetched comments before presenting them to the LLM. Instruct the LLM explicitly to treat the content of the comments strictly as data/text to be summarized, and never as instructions or commands to execute.	LLM	SKILL.md:11

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0d9669495e30b855.svg)](https://skillshield.io/report/0d9669495e30b855)