RSSaurus - Agent-Friendly RSS Feed Reader
v1.0.1Use the RSSaurus command-line client (Go binary `rssaurus`) to interact with https://rssaurus.com from the terminal: authenticate (`rssaurus auth login/whoami`), list feeds/items, print item URLs for piping, open URLs, and perform triage actions (mark read/unread, bulk mark-read, save/unsave). Use when asked to automate RSSaurus tasks from CLI, debug token/config issues, or demonstrate command usage.
⭐ 1· 3.3k·4 current·4 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the instructions: the SKILL.md simply documents/runtime-instructions for using the rssaurus CLI (auth, list feeds/items, mark read/save, open URLs). There are no unrelated requirements (no cloud creds, no unrelated binaries).
Instruction Scope
Instructions are narrowly scoped to running the rssaurus binary and handling its JSON/output flags. The doc explicitly warns not to print config files (which may hold tokens) and limits what user data to request. It does not instruct reading unrelated system files or exfiltrating data.
Install Mechanism
There is no install spec (instruction-only). The SKILL.md references official project and Homebrew links for context; nothing in the skill attempts to download or write code to disk.
Credentials
The skill does not declare or require any environment variables, credentials, or config paths. The instructions sensibly avoid printing CLI config containing API tokens.
Persistence & Privilege
No special privileges requested: always is not set and model invocation is not disabled (default). That is an acceptable configuration here because the skill does not carry additional credentials or install persistent agents.
Assessment
This skill is a documentation-style helper for using an existing rssaurus CLI. Before installing/using: ensure the rssaurus binary is from the official repo/Homebrew tap linked in the SKILL.md, do not paste or display API tokens or CLI config, and confirm you trust the machine-level binary the skill will run. If you prefer the model not run CLI commands autonomously, consider disabling model invocation for the skill in your agent settings.Like a lobster shell, security has layers — review code before you run it.
latestvk97c4387g3f85w1nxykarc3a2980p2w5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
