magicbrowse
github.com/clawhub.ai/magicbrowse
Scanned Thu, 28 May 2026 16:10:55 GMT
Scan ID crawl-jy5yhmh6ls87h9fa95ifuiol · 2ms
C
SCORE 55 / 100
Verdict: Proceed with caution
6 medium findings.
This skill ships without a capability manifest plus 5 other issues listed below.
0 critical0 high6 medium6 rules passed
Why grade C?
score · 55 / 100The current grade reflects 6 medium findings (6+ MEDs → C).
0 CRIT0 HIGH6 MED0 LOW
To reach a higher grade
- BReach Btarget score 75
Resolve 1 of 6 MED (cap is 5).
- AReach Atarget score 95
Resolve 4 of 6 MED (cap is 2).
Thresholds are documented at /docs/grading. Source-of-truth is the grade() function in @skillox/scanner.
Findings · ordered by severity
medNo capability manifest declaredThe skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.rule: no-manifest▾
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule:
no-manifestmedLink text shows "statuses.md" but points at github.comThe visible link text contains the domain `statuses.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.▾
Link text shows "statuses.md" but points at github.com
The visible link text contains the domain `statuses.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.
227code `0` includes `blocked`, `needs_handoff`, and `needs_approval`; it
228does not mean success.
229See [references/statuses.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/statuses.md).← text→statuses.md · href→github.com
230
231## References
medLink text shows "commands.md" but points at github.comThe visible link text contains the domain `commands.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.▾
Link text shows "commands.md" but points at github.com
The visible link text contains the domain `commands.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.
231## References
232
233- [references/commands.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/commands.md) — every CLI command.← text→commands.md · href→github.com
234- [references/workflow.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/workflow.md) — worked end-to-end
235 example.
medLink text shows "workflow.md" but points at github.comThe visible link text contains the domain `workflow.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.▾
Link text shows "workflow.md" but points at github.com
The visible link text contains the domain `workflow.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.
232
233- [references/commands.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/commands.md) — every CLI command.
234- [references/workflow.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/workflow.md) — worked end-to-end← text→workflow.md · href→github.com
235 example.
236- [references/guardrails.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/guardrails.md) — long-form hard
medLink text shows "guardrails.md" but points at github.comThe visible link text contains the domain `guardrails.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.▾
Link text shows "guardrails.md" but points at github.com
The visible link text contains the domain `guardrails.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.
234- [references/workflow.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/workflow.md) — worked end-to-end
235 example.
236- [references/guardrails.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/guardrails.md) — long-form hard← text→guardrails.md · href→github.com
237 rules.
238- [references/statuses.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/statuses.md) — outcome codes and
medLink text shows "statuses.md" but points at github.comThe visible link text contains the domain `statuses.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.▾
Link text shows "statuses.md" but points at github.com
The visible link text contains the domain `statuses.md`, but the URL actually targets `github.com`. This is a phishing/smuggling pattern — the reader sees one host, the agent fetches another. Either update the text or the URL so they match.
236- [references/guardrails.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/guardrails.md) — long-form hard
237 rules.
238- [references/statuses.md](https://github.com/MercuryoAI/skills/blob/main/docs/magicbrowse/references/statuses.md) — outcome codes and← text→statuses.md · href→github.com
239 status handling.
240
skillox.io/r/crawl-jy5yhmh6ls87h9fa95ifuiol