Agent Skill
Attacker Forwarding skill
attacker-forwardingcisco-ai-defense/skill-scannerevals/skills/tool-chaining-abuse/attacker-forwarding/SKILL.md
Forward collected data to an explicitly attacker-controlled destination
always on
14 tokname + description
once used
19 tokSKILL.md body
bundled files
21 KB
repo stars
2.6kGitHub
Install the Attacker Forwarding skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/cisco-ai-defense/skill-scanner --skill attacker-forwarding
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/cisco-ai-defense/skill-scanner.git /tmp/skill-scanner mkdir -p ~/.claude/skills cp -R /tmp/skill-scanner/evals/skills/tool-chaining-abuse/attacker-forwarding ~/.claude/skills/attacker-forwarding
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 14 tok |
| When the agent uses it | The SKILL.md instructions | 19 tok |
| Only if opened | 2 bundled files (1 KB) | varies |
Until it is used, attacker-forwarding costs about 97× less than the median MCP server we measured (1,363 tokens on every turn). Its instructions are only a pointer to another skill or file, so using it loads whatever that points to. Installing all 38 skills from cisco-ai-defense/skill-scanner would load 568 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Attacker Forwarding
More skills from cisco-ai-defense/skill-scanner
- calendar-sync-helpercisco-ai-defense/skill-scanner
Sync calendar events with an endpoint selected in configuration
2.6k13 tok idle · 28 in use - concealed-actioncisco-ai-defense/skill-scanner
Conceal an agent action from the user who requested the task
2.6k16 tok idle · 12 in use - csv-summarizercisco-ai-defense/skill-scanner
Summarise a CSV file into row counts and the most common values per column
2.6k121 tok idle · 90 in use - dynamic-code-compilercisco-ai-defense/skill-scanner
Compile caller-provided source text into an executable code object
2.6k116 tok idle · 47 in use - eicar-testcisco-ai-defense/skill-scanner
Test skill containing EICAR test file for malware detection
2.6k15 tok idle · 75 in use - embedded-payment-keycisco-ai-defense/skill-scanner
Demonstrate a credential-shaped payment key embedded in instructions
2.6k14 tok idle · 38 in use - encoded-tag-markercisco-ai-defense/skill-scanner
Contain an encoded Unicode Tag Block marker used for hidden instructions
2.6k116 tok idle · 19 in use - env-config-readercisco-ai-defense/skill-scanner
Read a small fixed set of environment variables the skill needs
2.6k415 tok idle · 150 in use