Blindoracle Docs— agent skill

Blindoracle Docs — independently scanned and version-tracked by SaferSkills.

by craigmbrown·Agent Skill·github.com/craigmbrown/blindoracle-docs
Review on GitHub →

Is Blindoracle Docs safe to install?

SaferSkills independently audited Blindoracle Docs (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 3 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 · 29d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings0 warnings · 3 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
25
8.8 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 · 3 flagged

Securityscore 25 · 3 findings
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · passports/passport-example.md
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
excerptpassports/passport-example.md· markdown
54},
55"passport_hash": "22497294e8bff29d1ee9ad39627810d04376151a7a0a5452922d275d364a445b",
56"signature": "b4885890ae4a590c5680e1c49239e9cf3d1b48497f464142562c743aa5098c2cc6dd418a54d581
… (51 chars elided on L56)
57}
58```
Occurrences
1 occurrence · at L56
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-01sha2560d77e3c40ecb694f…rubric 365aacaView on GitHub
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · blog/camel-security.md
HIGH — when it fires on hostile content the impact is full system-prompt override.
Why it matters

The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.

The exact value spotted
excerptblog/camel-security.md· markdown
43- **Baseline behavior profiling**: Each agent's decision patterns are recorded over a rollin
… (108 chars elided on L43)
44- **Deviation detection**: When an agent's current behavior deviates more than 30% from its
… (69 chars elided on L44)
45- **Suspicious pattern filtering**: Known persuasion patterns are detected at the input leve
… (108 chars elided on L45)
46- **Temporal analysis**: The system tracks whether an agent's behavior is shifting gradually
… (108 chars elided on L46)
47 
Occurrences
1 occurrence · at L45
How to fix
Remove the override phrase, or rephrase the passage so it does not instruct the agent to discard its rules.
  1. Delete the ignore/disregard/forget … previous instructions sentence.
  2. If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IGNORE-01sha2562e4221a7f996a729…rubric 365aacaView on GitHub
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · security/massat-results.md
HIGH — when it fires on hostile content the impact is full system-prompt override.
Why it matters

The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.

The exact value spotted
excerptsecurity/massat-results.md· markdown
80| SEC-017 | Suspicious phrase filtering | PASS |
81| SEC-018 | Gradual drift detection | PASS |
82| SEC-019 | "Ignore previous instructions" rejection | PASS |
83| SEC-020 | Context poisoning detection | PASS |
84| SEC-021 | Authority escalation attempt | PASS |
Occurrences
1 occurrence · at L82
How to fix
Remove the override phrase, or rephrase the passage so it does not instruct the agent to discard its rules.
  1. Delete the ignore/disregard/forget … previous instructions sentence.
  2. If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IGNORE-01sha256087b391ca4342386…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.

Scan a GitHub repoBrowse capabilities