feedback-page-generator
v1.0.1When the user wants to create, optimize, or audit a feedback or roadmap page. Also use when the user mentions "feedback page," "roadmap," "feature requests,"...
⭐ 0· 80·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name and description align with its instructions: it provides guidance and copy for feedback/roadmap pages and mentions common integrations (Canny, FeatureBase, UserVoice). One small inconsistency: the metadata declares no required config paths, but the SKILL.md explicitly tells the agent to read .claude/project-context.md or .cursor/project-context.md if present. Reading local project-context files is reasonable for this purpose but the metadata omission is worth noting.
Instruction Scope
SKILL.md is focused and stays on-task (page structure, copy, integration notes, SEO). The only runtime file access it requests is to read optional project-context files in the repository (.claude/... or .cursor/...). This is coherent with the goal but is a concrete action that will surface local project information; the instructions do not direct reading of unrelated system files, environment variables, or external endpoints.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only. That is the lowest-risk install model and matches the skill's described function.
Credentials
The skill requires no environment variables, no credentials, and no config paths in its metadata. It mentions third-party services (Canny, FeatureBase, UserVoice) but does not request API keys or instruct automatic integration. The absence of credential requests is proportionate to an authoring/advisory skill.
Persistence & Privilege
always is false and the skill is user-invocable; autonomous invocation is enabled by default (normal platform behavior). The skill does not request persistent privileges or modify other skills. Combined with no credentials and no installs, there is no concerning persistence or privilege escalation.
Assessment
This skill is instruction-only and appears to be what it claims: a helper for feedback/roadmap pages. Before installing, consider: (1) It will read optional project-context files (.claude/project-context.md or .cursor/project-context.md) if they exist — if those files contain sensitive information you do not want exposed to skills, remove or redact them. (2) The skill mentions integrations (Canny, FeatureBase, UserVoice) but does not request API keys or perform network calls — any actual integration will require you to supply credentials separately, so verify those steps before granting access. (3) Because the skill can be invoked autonomously by the agent, limit autonomous use if you do not want the agent to open project files without your prompt. Overall risk is low, but if you want maximum certainty, review SKILL.md directly and run the skill in a controlled environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk973mywy6dkhm4ykp2tfyezvh9841214
License
MIT-0
Free to use, modify, and redistribute. No attribution required.