Security audit

BugHerd

Security checks for vulnerabilities and agentic risk

Overview

This BugHerd skill is mostly coherent, but its setup instructions use unverified remote installer scripts that need user review before installation.

Install this only if you trust OOMOL's oo CLI distribution path and your BugHerd account use case. Prefer a signed or checksum-verified installer instead of running the documented curl|bash or irm|iex commands blindly, and review exact payloads before approving create or update actions in BugHerd.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:68
Finding: Unverified Remote Installer Scripts Executed Directly by Shells
Content: View full analysis
Remediation: View remediation
/install.sh" echo " oo-install.sh" | sha256sum --check - less oo-install.sh bash oo-install.sh ``` The checksum must be obtained through a trustworthy, independently authenticated release channel. Windows installation should similarly download a version-pinned artifact, validate its Authenticode signature or published digest, and execute it only after explicit approval. ]]>

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (2)

External Script Fetching

High

Category: Supply Chain
Confidence: 97% confidence
Finding: The skill instructs users to install software by piping a remotely fetched script directly into bash, which creates a classic supply-chain and remote code execution risk. If the install endpoint, CDN, TLS trust chain, or upstream distribution is compromised, arbitrary code would execute immediately on the user's machine without inspection.
Content: Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):

bash
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux

powershell

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description says to use this skill for 'ANY BugHerd request' and 'Whenever a task involves BugHerd,' which is an intentionally broad activation condition for a manifest/markdown file. It does not provide negative examples or constraints, so the trigger scope could overlap with many ordinary requests that merely mention BugHerd.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.