CC appstore-api
Apple App Store API for AI agents — search iOS apps by name, keyword, App Store ID or bundle ID, then retrieve metadata, ratings, reviews, developers, privacy labels, similar apps, and competitors as structured JSON. Use for App Store search, ASO research, iOS app review analysis, ratings lookup, developer lookup, and mobile app competitive analysis. Free keyless first request, read-only public data; no account or API key is required for the anonymous path.
Apple App Store API for AI agents — search iOS apps by name, keyword, App Store ID or bundle ID, then retrieve metadata, ratings, reviews, developers, privacy…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-credential-useINSTALL.md:41Credential used in a network call (verify the destination is the intended service)curl -sS -H "Authorization: Bearer $REPLYNODES_API_KEY" \
-
low Exfiltration
net-credential-usellms.txt:9Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)Auth: `Authorization: Bearer $REPLYNODES_API_KEY`, sent only to https://api.replynodes.com — the
quoted -
low Exfiltration
net-credential-usereferences/endpoints.md:12Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)document these references were generated from; `curl -sS -H "Authorization: Bearer $REPLYNODES_API_KEY"
quoted -
low Exfiltration
net-credential-useSKILL.md:94Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)`Authorization: Bearer $REPLYNODES_API_KEY` only to `https://api.replynodes.com`.
quoted -
low Exfiltration
net-credential-useSKILL.md:192Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)AUTH="Authorization: Bearer $REPLYNODES_API_KEY" # sent only to https://api.replynodes.com
quoted
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 38, column 7: auth: No key or account for the anonymous first-request path; optional authenti… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "contract_version" - note
frontmatter-keyunknown frontmatter key "mode" - note
frontmatter-keyunknown frontmatter key "keywords" - note
frontmatter-keyunknown frontmatter key "search_terms" - note
frontmatter-keyunknown frontmatter key "entrypoint" - note
frontmatter-keyunknown frontmatter key "auth"
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 17 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 47 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3750 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 tags): a typed call is more reliable
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)
- +2Single-language instructions
- +3Description length 461: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.