SKILLEMALL.ai
RU Sign in

BF engram

Persistent semantic memory for AI agents. Store, search, recall, and forget memories across sessions using Qdrant + FastEmbed.

ClawHub Agent Skills author: engram v2.1.0 MIT-0 49 files · 2 scripts body ≈ 3 197 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 38/100 · Will not run — References files that are not bundled: OPENCLAW_INTEGRATION.md

ProcedureInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
79/100
safety, quality, tests
Safety 60%
88
Quality 40%
65
Run on models
none yet
Process rating
F
38/100
Will not run
References files that are not bundled: OPENCLAW_INTEGRATION.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Dangerous commands cmd-shell-rc scripts/setup-context.sh:84
    Writes to a shell startup file
    echo "export PATH=\"$COMMANDS_DIR:\$PATH\"" >> "$HOME/.bashrc"
  • medium Dangerous commands cmd-shell-rc scripts/setup-context.sh:86
    Writes to a shell startup file
    echo -e "${YELLOW}   Run: source ~/.bashrc  (or restart terminal)${NC}"
  • low Exfiltration read-dotenv context/templates/web_app.yaml:566
    Reads a .env file (quoted — discussed, not commanded)
    cp .env.example .env
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:61
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…wQp+7C4n…9JQ==",
    detector

Files scanned: 46. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: OPENCLAW_INTEGRATION.md

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: OPENCLAW_INTEGRATION.md
  • 0Tools and files. 1 referenced file(s) missing: OPENCLAW_INTEGRATION.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (engram) differs from the folder (engrammemory)
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 47 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 3197 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • -37 of 9 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 126: enough signal without eating the budget
  • +4Structure: 49 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (29 code blocks)
  • +4Reference files are cited in the instructions (2 of 9)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: suspicious
Engram’s memory features are coherent, but it should be reviewed because it defaults to persistent capture/recall of user content and makes lasting local environment changes during setup.
LLM: suspicious (high) · VirusTotal: · 29 May 2026