DD health-management-enhanced
(no description)
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
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.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Add a description to the frontmatter: without it the skill never triggers.
- 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 · 15
-
high Dangerous commands
cmd-persistencescripts/activate_health_skill.sh:75Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "$CRON_LINE") | crontab -
Medium and low: 14
-
medium Broad scope
meta-agent-memory-dumpHEARTBEAT.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensHEARTBEAT.md
-
medium Dangerous commands
cmd-eval-dynamicscripts/activate_health_skill.py:99Dynamic code execution from decoded/untrusted inputos.system(f'"{script_path}"') -
medium Secrets in code
secret-labelled-tokenscripts/daily_health_reminder.py:28Labelled token / key literal (vendor format unknown — verify it is not a live credential)APP_SECRET = "JrMN…ZRR"
-
medium Secrets in code
secret-labelled-tokenscripts/daily_health_reminder.sh:24Labelled token / key literal (vendor format unknown — verify it is not a live credential)APP_SECRET="JrMN…ZRR"
-
low Dangerous commands
cmd-cron-mentionscripts/activate_health_skill.py:74Mentions editing / listing crontab (string literal in code, not executed)current_cron = subprocess.check_output("crontab -l 2>/dev/null", shell=True).decode("utf-8")code literal -
low Dangerous commands
cmd-cron-mentionscripts/activate_health_skill.py:118Mentions editing / listing crontab (string literal in code, not executed)print(" crontab -e")code literal -
low Dangerous commands
cmd-cron-mentionscripts/activate_health_skill.sh:71Mentions editing / listing crontabif crontab -l 2>/dev/null | grep -q "daily_health_reminder"; then
-
low Dangerous commands
cmd-cron-mentionscripts/activate_health_skill.sh:75Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "$CRON_LINE") | crontab -
-
low Dangerous commands
cmd-cron-mentionscripts/activate_health_skill.sh:104Mentions editing / listing crontab (string literal in code, not executed)echo " crontab -e"
code literal -
low Dangerous commands
cmd-cron-mentionscripts/auto_bind_user.py:54Mentions editing / listing crontab (quoted — discussed, not commanded)cron_list = os.popen("crontab -l 2>/dev/null").read()quoted -
low Dangerous commands
cmd-cron-mentionscripts/auto_bind_user.py:76Mentions editing / listing crontab (string literal in code, not executed)current_cron = subprocess.check_output("crontab -l 2>/dev/null", shell=True).decode("utf-8")code literal -
low Dangerous commands
cmd-cron-mentionscripts/auto_bind_user.py:91Mentions editing / listing crontab (quoted — discussed, not commanded)cron_list = os.popen("crontab -l 2>/dev/null").read()quoted -
low Secrets in code
secret-high-entropy-tokenscripts/daily_health_reminder.py:28High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)APP_SECRET = "JrMN…ZRR"
quoted -
low Secrets in code
secret-high-entropy-tokenscripts/daily_health_reminder.sh:24High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)APP_SECRET="JrMN…ZRR"
quoted
Files scanned: 40. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-missingSKILL.md: no `description` — the skill can never trigger - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "autoclaw.schema" - note
frontmatter-keyunknown frontmatter key "channels" - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (health-management-enhanced) differs from the folder (healthai)
- 100Tools and files. No external tools needed
- 100Steps. 53 steps
- 100Execution cost. Instruction body is 725 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -315 of 17 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 26.