1 check that ran failed — version behavior — so this release can’t be trusted as-is.
- Publisher
- io.github.VonderVuflya
- Repository
- github.com/VonderVuflya/yggdrasil
- Install
- pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory, pypi:yggdrasil-memory
- Versions
- 24
- Inspected
- 5 of 6 checks · 75%
- Scored
- 2026-09-03 · rubric 1.0.0
What we checked
Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.
Injection surface
unscannable25% of gradeTool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).
No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.
Supply chain
pass25% of gradePackage provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.
Python build script has no build-time network/exec; repository linkage verified
Credential hygiene
warn15% of gradeHow the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.
tests/test_ygg_memory_server.py: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) Reads secrets from the environment (e.g. eval/ygg_eval.py) — the recommended intake shape.
Permission scope
warn15% of gradeDeclared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.
has both shell/exec and network egress — capable of download-and-run, though no such path was observed (yggdrasil/cli.py: subprocess.* call; scripts/release.sh: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (yggdrasil/cli.py: subprocess.* call; eval/ygg_eval.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: 13 files (yggdrasil/cli.py, yggdrasil/service.py, yggdrasil/ygg_cross_agent_demo.py, +10 more) discloses broad/destructive filesystem access: 8 files (eval/ygg_eval.py, yggdrasil/install.sh, yggdrasil/install.sh, +5 more) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.
Version behavior
fail10% of gradeDiff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).
vs prior 0.13.2 (minor bump): new capability primitive(s) in source: child_process, fs-write, net, subprocess; new hardcoded outbound host/BCC destination(s): 127.0.0.1, 192.168.3.124, box, config, env, flag, github.com, ollama.com, pypi.org, www.apple.com.
Transport config
warn10% of gradeRemote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.
manifest/source references check for updates behavior — disclosure
Version history
Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.
| Version | Published | Grade | Score | Inspected | Change |
|---|---|---|---|---|---|
| v0.15.0 · current | 2026-08-06 | C | 70 | 5/6 · 75% | B→C in v0.15.0 |
| v0.13.2 | 2026-07-18 | B | 100 | 3/6 · 55% | ±0 |
| v0.13.0 | 2026-07-17 | B | 80 | 4/6 · 65% | ±0 |
| v0.9.1 | 2026-07-04 | B | 87.5 | 4/6 · 65% | — |