DC instagram-downloader
Download Instagram profile media (reels MP4, photos JPG, full carousel multi-image JPG) via sessionid (instagrapi), Apify dataset fallback, or interactive setup wizard. No password sharing required.
Download Instagram profile media (reels MP4, photos JPG, full carousel multi-image JPG) via sessionid (instagrapi), Apify dataset fallback, or interactive…
As a process C 60/100 · Has gaps — weak spots: result and completion, consistency
The same skill appears in 1 more place: ClawHub
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 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.
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.
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 8
-
high Exfiltration
intent-browser-credential-storeCHANGELOG.md:86Accesses a browser credential / cookie storechanges (Chrome 127+ moved to `Network/Cookies`). Playwright bypasses all of these.
-
high Dangerous commands
cmd-pipe-to-shellREADME.md:239Downloads and executes remote code from an unrecognised host (pipe to shell)iex (iwr -Uri https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.ps1).Content
Medium and low: 6
-
medium Exfiltration
intent-browser-credential-storeinstagram_downloader.py:128Accesses a browser credential / cookie store (quoted — discussed, not commanded)"Google/Chrome/User Data/Local State"
quoted -
medium Dangerous commands
cmd-pipe-to-shellREADME.md:28Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| **Windows PowerShell** | `iex (iwr -Uri https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.ps1).Content` |
table -
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:122Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:236Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.sh | bash
-
low Dangerous commands
cmd-pipe-to-shell-known-hostinstall.sh:15Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)# curl -fsSL https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.sh | bash
comment -
low Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:27Pipe-to-shell installer from a well-known host (still executes remote code) (documentation table row)| **Linux / macOS / Git Bash** | `curl -fsSL https://raw.githubusercontent.com/cripterhack/ig-downloader-skill/main/install.sh \| bash` |
table
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 198 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "type"
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (instagram-downloader) differs from the folder (igd)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 24 steps
- 100Execution cost. Instruction body is 3336 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- -218 emoji in the instructions: noise for the model
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 198: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (15 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.