Security audit
Security checks for vulnerabilities and agentic risk
This frontend debugging skill is coherent and not malicious, but it asks agents to collect and save potentially sensitive diagnostic data without clear redaction or user-control safeguards.
Review this skill before installing if your frontend work involves production traffic, customer data, private APIs, or secrets in headers and environment variables. Use it only with sanitized logs and reports, and redact Authorization, Cookie, API keys, tokens, PII, internal URLs, and sensitive payloads before saving or sharing diagnostic output.
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
- ID: `fec-debug-framework`
- Category: `review-quality`
- Version: `2.9.0`
- Source: `skills/fec-debug-framework/SKILL.md`
## Description
The invocation description uses very broad terms such as 'debugging', 'troubleshooting', and 'error reporting', which can cause the skill to activate in many ordinary conversations unrelated to this specific framework. Over-broad triggers increase the chance of unintended invocation, exposing users to unnecessary guidance, workflow hijacking, or misrouting of tasks to this skill when a narrower tool would be more appropriate.
The manifest description says to use the skill for a very wide range of issues and includes generic trigger terms like "debugging," "debug," "troubleshooting," and "error reporting." These phrases are common in everyday developer conversation and the file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.
The API debugging steps instruct collection of request URLs, headers, bodies, response data, and cached state, which commonly contain secrets, tokens, session identifiers, PII, or business-sensitive payloads. Without explicit minimization, redaction, or user warning, the skill can lead to unnecessary exposure of sensitive data during debugging and downstream handling.
The manifest description says to use the skill for a wide range of situations and includes generic trigger terms such as "debugging," "debug," "troubleshooting," and "error reporting." These terms are broad enough to match ordinary conversation and the file does not provide explicit constraints or negative examples to narrow when the skill should or should not activate.
The description uses very broad activation phrases such as debugging, troubleshooting, runtime errors, request failures, and exceptions, which are common across many normal support interactions. In an agent-skill ecosystem, this can cause over-triggering and unintended invocation, expanding the skill's opportunity to influence workflows beyond narrowly intended frontend debugging scenarios.
The template explicitly encourages collecting and persisting diagnostic artifacts such as environment variables and status snapshots, which commonly contain secrets, tokens, internal URLs, or user data. Because the report is then saved to a predictable file path, sensitive information may be unnecessarily retained, shared, or committed without redaction guidance.
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
## Purpose
Use an evidence-driven triage, collection, hypothesis, verification, and remediation process to locate front-end faults and avoid relying on intuition to expand the scope of changes.
## Procedure
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
## Purpose
Use an evidence-driven triage, collection, hypothesis, verification, and remediation process to locate front-end faults and avoid relying on intuition to expand the scope of changes.
## Procedure
Requiring a diagnostic report to be saved to disk creates a persistence risk because the report may include logs, stack traces, requests, responses, or state snapshots gathered earlier in the process. If sensitive evidence is written unsanitized to local storage, repositories, shared workspaces, or tickets, it increases the chance of credential leakage, privacy exposure, and long-term retention beyond the immediate debugging need.
The manifest explicitly states that Chinese triggers are included, but it does not indicate that language selection is optional or user-driven. That can be a locale/language policy concern because the skill defines language-specific activation behavior without documenting user choice or a region-specific reason.
No suspicious patterns detected.