Security audit

Software Data Github Interact Developer Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only developer helper skill with overly broad activation wording, but no hidden execution, persistence, credential handling, or destructive behavior was found.

Installers should treat this as a broad developer-assistance helper and be aware it may activate on generic GitHub, CLI, API, or issue-related prompts. Confirm before allowing any downstream agent action that edits a repository or interacts with GitHub remotely.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad enough to match routine software, GitHub, CLI, or issue-related requests, which can cause the skill to activate in contexts the user did not specifically intend. In an agent environment, overbroad invocation increases the chance of unnecessary repository-affecting guidance or tool use without clear user consent, especially because the skill is framed around practical GitHub-style workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is extremely broad and includes common workflow terms like GitHub, CLI, issue, analysis, and implementation support without tight scope boundaries. This can cause the skill to be selected for many unrelated prompts, increasing the chance that a user is routed into an unintended workflow or receives actions/automation outside the original requirement.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list uses highly generic keywords such as 'run', 'api', 'issue', and 'github' with no scope constraints, which materially raises the chance of unintended invocation. In an agent environment, over-triggering is dangerous because it can steer unrelated user requests into this skill's workflow, causing incorrect guidance, unnecessary tool usage, or accidental interaction with repositories and developer systems.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrase is so broad that ordinary user requests about GitHub, software, bugs, or workflows could activate the skill unintentionally. This increases the chance of incorrect routing, unintended execution paths, and prompt-scope confusion, especially in an agent ecosystem where skill activation may grant the skill influence over the response flow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are overly broad and map to common requests such as asking for help or needing a practical workflow, which can cause the skill to activate unintentionally for unrelated conversations. In an agent ecosystem, accidental invocation can route users into the wrong workflow, create confused delegation, and increase exposure to downstream actions involving GitHub-style operations.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The README promotes GitHub-style workflow support involving issues, PRs, CLI, and API interactions, but does not warn that these actions may modify local repositories or trigger remote-side effects such as opening issues, pushing branches, or changing project state. In an agent-assisted workflow, missing safety language can lead users to authorize or expect actions without understanding the operational impact.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list includes very generic terms such as run, api, issue, and github, which are common across many unrelated user requests. This can cause unintended invocation of the skill, leading the agent to apply this workflow in contexts it was not designed for, increasing the chance of incorrect guidance, overbroad actions, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are broad, incomplete, and resemble ordinary help requests rather than clear invocation patterns. Because they overlap with common developer-assistance language, they may spuriously activate the skill for unrelated tasks, causing misrouting and reducing reliability of agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The default prompt and short description are overly broad and vague, describing many possible software, data, GitHub, CLI, issue, workflow, artifact, checklist, analysis, and implementation tasks without defining clear boundaries. This increases the chance of unintended routing or invocation for requests outside the intended scope, which can expose users to irrelevant or risky actions initiated by the skill under weak matching criteria.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without narrowing context allows the platform to auto-select this skill based on loose semantic matches, even when the user's intent is ambiguous. Because this skill is framed around broad GitHub-style and developer-helper workflows, the combination materially raises the risk of overbroad activation, unexpected actions, or the skill influencing tasks it was not specifically requested to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The activation scope is ambiguous because the natural-language trigger is unspecific and could match many unrelated requests. In practice, this can cause the wrong skill to be selected, exposing users to irrelevant or lower-quality guidance and creating an avenue for skill hijacking by overly generic activation patterns.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.