Glyphs Info Mcp— agent skill

Glyphs Info Mcp — independently scanned and version-tracked by SaferSkills.

by yintzuyuan·Agent Skill·github.com/yintzuyuan/glyphs-info-mcp

Is Glyphs Info Mcp safe to install?

SaferSkills independently audited Glyphs Info 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 4 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
45/100
●●●●●○○○○○
Re-scan~30s
Latest scan
ScannedJun 25, 2026 · 132d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings1 warnings · 4 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 · 5 flagged

Securityscore 0 · 5 findings
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · src/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json×4
HIGH — once 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
excerptsrc/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json· json
1164},
1165"end": {
1166"$id": "#/properties/glyphs/items/properties/layers/items/properties/shapes/items/path/prope
… (47 chars elided on L1166)
1167"type": "array"
1168}
Occurrences
4 occurrences · first at L1166, also L1179, L1205 +1 more
Show all 4 locations
Line
File
L1166
src/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json
L1179
src/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json
L1205
src/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json
L1209
src/glyphs_info_mcp/data/official/GlyphsSDK/GlyphsFileFormat/validator/Glyphs3FileSchema.json
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-01sha2563b096e4223527891…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · src/glyphs_info_mcp/data/official/GlyphsSDK/Python Templates/README.md
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
excerptsrc/glyphs_info_mcp/data/official/GlyphsSDK/Python Templates/README.md· markdown
143- Other **IBOutlets**: Ctrl-drag from the *File’s Owner* to a UI element (e.g. text field),
… (57 chars elided on L143)
144- **IBActions**: Ctrl-drag from a UI element (e.g. button) to the *File’s Owner* in the left
… (76 chars elided on L144)
145- **Only for File Format Plugin:** In the left-side objects side bar choose *Custom View*, a
… (108 chars elided on L145)
146 
147All the back and forth relations between the UI and your Python code can be reviewed in the
… (47 chars elided on L147)
Occurrences
1 occurrence · at L145
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-01sha25615dae9807bd892c6…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.