content— mcp server

content — independently scanned and version-tracked by SaferSkills.

Is content safe to install?

SaferSkills independently audited content (MCP Server) and scored it 66/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 8 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
66/100
●●●●●●●○○○
Re-scan~30s
Latest scan
ScannedJun 23, 2026 · 134d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings8 warnings · 0 high
EngineSaferSkills 755a9a5
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
4
1.4 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 8 flagged

Securityscore 4 · 8 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · site/content/built-in/modes/MODES.md×3
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptsite/content/built-in/modes/MODES.md· markdown
13| **Plan** | Reads only, no edits | Exploring before you change anything |
14| **Auto** | Everything, with background safety checks | Long tasks, fewer interruptions |
15| **Don't Ask** | Only pre-approved tools | Locked-down CI and scripts |
16| **Bypass Permissions** | Everything, no checks | Isolated containers and VMs only |
17 
Occurrences
3 occurrences · first at L15, also L46, L56
Show all 3 locations
Line
File
L15
site/content/built-in/modes/MODES.md
L46
site/content/built-in/modes/MODES.md
L56
site/content/built-in/modes/MODES.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256916b0a531165cbd7…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · site/content/built-in/modes/permission-modes/permission-modes.md×5
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptsite/content/built-in/modes/permission-modes/permission-modes.md· markdown
1# Permission Modes
2 
3Four of the built-in modes trade oversight for convenience without a safety classifier: **Ma
… (108 chars elided on L3)
4 
5## Manual
Occurrences
5 occurrences · first at L3, also L24, L29 +2 more
Show all 5 locations
Line
File
L3
site/content/built-in/modes/permission-modes/permission-modes.md
L24
site/content/built-in/modes/permission-modes/permission-modes.md
L29
site/content/built-in/modes/permission-modes/permission-modes.md
L64
site/content/built-in/modes/permission-modes/permission-modes.md
L81
site/content/built-in/modes/permission-modes/permission-modes.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256916b0a531165cbd7…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.