MCP server · trust report

io.github.VonderVuflya/yggdrasil

1 check that ran failed — permission scope — 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
Versions
22
Inspected
4 of 6 checks · 65%
Scored
2026-07-21 · 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.

6 checks1 clean3 flagged2 not inspected
  • Injection surface

    unscannable25% of grade

    Tool 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 grade

    Package 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 grade

    How 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

    fail15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    HIGH: shell/exec capability AND network egress together — download-and-execute risk (yggdrasil/cli.py: subprocess.* call; scripts/release.sh: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (yggdrasil/cli.py: subprocess.* call; eval/ygg_eval.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: yggdrasil/cli.py: subprocess.* call discloses shell/exec capability: yggdrasil/service.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_cross_agent_demo.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_dense_gate.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_governance_gate.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_import_claude_memory.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_quality_gate.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_review_apply_gate.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_seed.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_setup.py: subprocess.* call discloses shell/exec capability: yggdrasil/ygg_sync.py: subprocess.* call discloses shell/exec capability: yggdrasil/hooks/ygg_session_start.py: subprocess.* call discloses shell/exec capability: yggdrasil/hooks/ygg_stop.py: subprocess.* call discloses broad/destructive filesystem access: eval/ygg_eval.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_quality.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_seed_distill.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_ygg_memory_server.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: yggdrasil/install.sh: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: yggdrasil/install.sh: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: yggdrasil/service.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: yggdrasil/service.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: yggdrasil/ygg_mcp_server.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: yggdrasil/ygg_memory_server.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: yggdrasil/ygg_review_actions.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: yggdrasil/ygg_seed.py: recursive glob ('**') from a broad root Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

  • Version behavior

    unscannable10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    no prior version to diff (first sight of io.github.VonderVuflya/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

  • Transport config

    warn10% of grade

    Remote 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.

VersionPublishedGradeScoreInspectedChange
v0.13.2 · current2026-07-18 C72.54/6 · 65%