RSSaurus - Agent-Friendly RSS Feed Reader

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: rssaurus Version: 1.0.1 The skill bundle provides instructions for using the `rssaurus` CLI tool, which aligns with its stated purpose. It includes explicit privacy notes in `SKILL.md` instructing the AI agent not to print sensitive configuration files containing API tokens, which is a strong indicator of benign intent and responsible design. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection attempts to subvert the agent's behavior beyond its intended function.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An overly broad command could mark many RSS items as read or change saved/read state in the user's account.

Why it was flagged

The skill documents account-state-changing CLI actions, including a bulk operation; this is disclosed and aligned with RSS triage, but broad writes should be intentional.

Skill content
Bulk mark read:

rssaurus mark-read --all
# or
rssaurus mark-read --ids 1,2,3
Recommendation

Use item IDs or feed filters for write actions where possible, and require explicit user confirmation before using `--all`.

What this means

Commands will act as the logged-in RSSaurus account, and exposing the config file could leak API tokens.

Why it was flagged

The skill relies on RSSaurus authentication and acknowledges token-bearing local config; this is expected for the integration and the artifact includes appropriate privacy guidance.

Skill content
Do **not** print (e.g. `cat`) the RSSaurus CLI config file contents; it can contain API tokens.
Recommendation

Verify the intended account with `rssaurus auth whoami`, do not display token files, and revoke/recreate tokens if they are exposed.

What this means

If the local `rssaurus` binary is not the expected one, RSSaurus account actions and authentication handling depend on that external executable.

Why it was flagged

The runtime instructions depend on a local `rssaurus` binary, but the supplied package does not install or pin that executable, so executable provenance is outside the skill artifact.

Skill content
No install spec — this is an instruction-only skill.
Recommendation

Install or update `rssaurus` from a trusted RSSaurus source and check `rssaurus --version` before using the skill for account actions.