Amcharts5 Mcp— agent skill

Amcharts5 Mcp — independently scanned and version-tracked by SaferSkills.

by amcharts·Agent Skill·github.com/amcharts/amcharts5-mcp

Is Amcharts5 Mcp safe to install?

SaferSkills independently audited Amcharts5 Mcp (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 22 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
45/100
●●●●●○○○○○
↑ +0 since first scan (45 → 45)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 34d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings0 warnings · 22 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
0
0.0 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 · 22 flagged

Securityscore 0 · 22 findings
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · extended/concepts/common-elements/buttons.md×2
HIGHonce decoded by the agent, an encoded payload has the same impact class as plain-text injection.
Why it matters

A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.

The exact value spotted
excerptextended/concepts/common-elements/buttons.md· markdown
254width: 32,
255height: 32,
256src: "data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiA/PjxzdmcgaGVpZ2h0PSIyMHB4IiB2ZXJz
… (104 chars elided on L256)
257cursorOverStyle: "pointer"
258})
Occurrences
2 occurrences · first at L256, also L268
Show all 2 locations
Line
File
L256
extended/concepts/common-elements/buttons.md
L268
extended/concepts/common-elements/buttons.md
How to fix
Remove the encoded blob, or decode it and review what it actually contains.
  1. Decode the base64 string and confirm it is not an instruction directed at the agent.
  2. Move any legitimate binary or signature data into a dedicated file (*.sig, SIGNATURES) outside the documentation.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-B64-PAYLOAD-01sha256fa4e5bb5701628aerubric 365aacaView on GitHub
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · extended/examples/column-bar/pictorial-column-chart.md×5
HIGHonce decoded by the agent, an encoded payload has the same impact class as plain-text injection.
Why it matters

A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.

The exact value spotted
excerptextended/examples/column-bar/pictorial-column-chart.md· markdown
15```javascript
16// Define icons
17var icon1 = "data:image/svg+xml;charset=utf-8;base64,PHN2ZyB3aWR0aD0iMTc2IiBoZWlnaHQ9Ijg4OSI
… (108 chars elided on L17)
18 
19var icon2 = "data:image/svg+xml;charset=utf-8;base64,PHN2ZyB3aWR0aD0iMTAzIiBoZWlnaHQ9IjU3NSI
… (108 chars elided on L19)
Occurrences
5 occurrences · first at L17, also L19, L21 +2 more
Show all 5 locations
Line
File
L17
extended/examples/column-bar/pictorial-column-chart.md
L19
extended/examples/column-bar/pictorial-column-chart.md
L21
extended/examples/column-bar/pictorial-column-chart.md
L23
extended/examples/column-bar/pictorial-column-chart.md
L25
extended/examples/column-bar/pictorial-column-chart.md
How to fix
Remove the encoded blob, or decode it and review what it actually contains.
  1. Decode the base64 string and confirm it is not an instruction directed at the agent.
  2. Move any legitimate binary or signature data into a dedicated file (*.sig, SIGNATURES) outside the documentation.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-B64-PAYLOAD-01sha2561c80bafe5dc4c434rubric 365aacaView on GitHub
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · extended/examples/timeline/linear-process-diagram.md×15
HIGHonce decoded by the agent, an encoded payload has the same impact class as plain-text injection.
Why it matters

A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.

The exact value spotted
excerptextended/examples/timeline/linear-process-diagram.md· markdown
12 
13```javascript
14var alarm = "data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iaXNvLTg4NTktM
… (108 chars elided on L14)
15var water = "data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iaXNvLTg4NTktM
… (108 chars elided on L15)
16var exercise = "data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iaXNvLTg4NT
… (108 chars elided on L16)
Occurrences
15 occurrences · first at L14, also L15, L16 +12 more
Show all 15 locations
Line
File
L14
extended/examples/timeline/linear-process-diagram.md
L15
extended/examples/timeline/linear-process-diagram.md
L16
extended/examples/timeline/linear-process-diagram.md
L17
extended/examples/timeline/linear-process-diagram.md
L18
extended/examples/timeline/linear-process-diagram.md
L19
extended/examples/timeline/linear-process-diagram.md
L20
extended/examples/timeline/linear-process-diagram.md
L21
extended/examples/timeline/linear-process-diagram.md
L22
extended/examples/timeline/linear-process-diagram.md
L23
extended/examples/timeline/linear-process-diagram.md
L24
extended/examples/timeline/linear-process-diagram.md
L25
extended/examples/timeline/linear-process-diagram.md
L26
extended/examples/timeline/linear-process-diagram.md
L27
extended/examples/timeline/linear-process-diagram.md
L28
extended/examples/timeline/linear-process-diagram.md
How to fix
Remove the encoded blob, or decode it and review what it actually contains.
  1. Decode the base64 string and confirm it is not an instruction directed at the agent.
  2. Move any legitimate binary or signature data into a dedicated file (*.sig, SIGNATURES) outside the documentation.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-B64-PAYLOAD-01sha256bcc9ce5e52ced84drubric 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.