Security audit
Security checks for vulnerabilities and agentic risk
This is a frontend debugging workflow skill with no executable payload, but users should redact sensitive diagnostic data before saving reports.
Install only if you want a structured frontend debugging workflow. Before saving or sharing generated reports, review and redact secrets, cookies, authorization headers, request bodies, environment values, internal URLs, customer data, and screenshots that may reveal private information.
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
Line L14 lists many broad activation cues such as "debugging," "troubleshooting," and "error reporting" without clearly constraining when the skill should or should not activate. It also does not provide negative examples or explicit scope boundaries, increasing the risk of unintended invocation for general help requests.
The skill description includes very broad trigger terms such as debugging, troubleshooting, exceptions, white screens, and request failures, which can cause the skill to activate for many ordinary engineering conversations. Over-broad activation increases the chance the agent will enter a diagnostic workflow unnecessarily, leading to unneeded file inspection, command suggestions, or report generation in contexts where the user did not explicitly request this skill.
The description contains very broad trigger terms such as 'debug', 'troubleshooting', 'error reporting', and 'exceptions', which can match routine conversation and cause the skill to activate outside its intended scope. In agent-routing systems, overbroad activation increases prompt-surface area and can unintentionally inject this skill's instructions into unrelated tasks, degrading control boundaries and enabling misuse.
The description includes very broad activation phrases such as 'debug', 'troubleshooting', 'runtime errors', and similar generic failure terms. In agent-routing systems, this can cause the skill to be invoked in many unrelated contexts, increasing the chance of unintended tool use, over-collection of context, or unsafe delegation to a skill the user did not explicitly request.
The template directs the agent to save a diagnostic report that may include logs, stack traces, screenshots, network traces, environment variables, and status snapshots, all of which can contain secrets, personal data, tokens, internal URLs, or customer information. Because it gives no instruction to redact sensitive fields, obtain user review, or minimize collected data before persisting it to disk, it creates a realistic risk of unintended data retention and disclosure.
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
The skill instructs saving a diagnostic report to a timestamped file but does not warn that the report may contain sensitive project details such as stack traces, request metadata, state snapshots, or internal paths. In a debugging skill, this context makes the issue more plausible because the workflow explicitly collects potentially sensitive operational data before writing it to disk.
The description explicitly introduces a language-specific trigger set with the phrase "Chinese triggers include," but the listed terms are predominantly English. This is a natural-language policy issue because it imposes or documents a locale-specific behavior inconsistently and without giving the user a clear language choice or explaining the constraint.
Line L04 explicitly states "Chinese triggers include..." in the activation description, introducing a language-specific behavior in natural language. There is no accompanying indication that language selection is optional or that the skill is intentionally limited to a Chinese-language deployment context.
No suspicious patterns detected.