Security audit

update-project-docs

Security checks for vulnerabilities and agentic risk

Overview

This documentation-updater skill is purpose-aligned and disclosed, though it can read and modify repository documentation when the user approves those actions.

Before installing, confirm you are comfortable with the skill reading your repository, proposing edits or deletions to docs, running local docs validation commands, and writing a .docs-sync file. Use it in a trusted repo or isolated clone if build scripts are untrusted, and require explicit review before commits.

SkillSpector

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

Confidence: 95% confidence
Finding: The manifest description lists specific trigger phrases but then broadens scope to "or mentions documentation updates in any project," which is ambiguous and lacks clear constraints. That wording could cause unintended invocation for ordinary conversation about documentation rather than explicit requests to run this skill.

Natural-Language Policy Violations

Low

Confidence: 97% confidence
Finding: The provided scaffold hard-codes `<html lang="en">`, which imposes an English locale in generated documentation infrastructure. The file does not offer a user choice or explain why English is required, so this is a natural-language locale policy issue under the stated rules.

Static analysis

No suspicious patterns detected.