SKILLEMALL.ai

FF project-context-manager

Project-based agent context management system for maintaining long-term memory and project state across sessions. Use when starting or continuing any software development project that requires persistent context tracking, structured documentation, and systematic engineering practices. This skill enforces PROJECT_CONTEXT.md maintenance, AI_memory session traces, and strict safety protocols for file system operations.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: 崔之行 v1.0.0 MIT-0 3 files body ≈ 2 818 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process F 46/100 · Will not run — References files that are not bundled: references/workflow-examples.md, references/code-templates.md, references/safety-checklist.md

ReferenceInfrastructureAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
F
36/100
safety, quality, tests
Safety 60%
10
Quality 40%
75
Run on models
none yet
Process rating
F
46/100
Will not run
References files that are not bundled: references/workflow-examples.md, references/code-templates.md, references/safety-checklist.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  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 · 1

  • critical Dangerous commands cmd-destructive-fs SKILL.md:262
    Destructive filesystem command (wipes root/home/drive)
    rm -rf /

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/workflow-examples.md
  • warning missing-ref reference to a missing file: references/code-templates.md
  • warning missing-ref reference to a missing file: references/safety-checklist.md

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: references/workflow-examples.md, references/code-templates.md, references/safety-checklist.md
  • 0Tools and files. 3 referenced file(s) missing: references/workflow-examples.md, references/code-templates.md, references/safety-checklist.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 6 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 52 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2818 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 419: enough signal without eating the budget
  • +4Structure: 40 headings
  • +3Step-by-step instructions: 52 items
  • +3Output format is stated explicitly
  • +4Has examples (20 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.

External checks

ClawHub: clean
This skill creates persistent project notes as advertised, with no evidence of hidden execution, exfiltration, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026