News Aggregator Skill
PassAudited by ClawScan on May 1, 2026.
Overview
The skill is coherently aimed at public news aggregation, with no code or credentials present, but it references missing helper files and may broaden user-requested filters.
This appears suitable as a public-news aggregation instruction set, but verify the missing fetch_news.py and templates.md files before use. Expect it to fetch article content from public sources, save local report files, and sometimes broaden time or keyword filters unless you ask for strict filtering.
Findings (2)
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.
The skill may not function as packaged, and any future or local helper file with these names should be reviewed before use.
The skill depends on a helper script and template file, but the supplied manifest contains only SKILL.md and no install spec. This is an incomplete-package/provenance note, not evidence of malicious behavior.
python3 scripts/fetch_news.py --source all --limit 15 --deep ... READ the content of `templates.md` in the skill directory.
Install only from a source that includes the referenced helper files, or review those files separately before allowing the agent to run them.
Reports may include older or broader items than the user strictly requested.
The instructions can intentionally broaden a user's requested time window when results are sparse. The skill also requires annotation of these older items, so this is a transparency note rather than a concern.
If the user requests a specific time window ... you MUST include high-value/high-heat items from a wider range (e.g. past 24h)
If exact filtering matters, ask the agent to use a strict time window or strict keyword match and exclude smart-fill items.