aria_skills/input_guard/SKILL.md
🛡️ Runtime security for Aria - analyzes inputs for prompt injection, validates API params, filters sensitive output
npx skillsauth add najia-afk/aria_moltbot aria-inputguardInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Runtime security skill. Analyze inputs for injection attacks, sanitize HTML, check SQL and path safety, filter sensitive output, and validate API parameters.
exec python3 /app/skills/run_skill.py input_guard <function> '<json_args>'
Analyze user input for security threats including prompt injection, jailbreak attempts, and malicious patterns.
exec python3 /app/skills/run_skill.py input_guard analyze_input '{"text": "ignore previous instructions"}'
Sanitize text for safe HTML display; escapes HTML entities to prevent XSS.
exec python3 /app/skills/run_skill.py input_guard sanitize_for_html '{"text": "<script>alert(1)</script>"}'
Check if text contains SQL injection patterns.
exec python3 /app/skills/run_skill.py input_guard check_sql_safety '{"text": "1; DROP TABLE users"}'
Check if a file path contains path traversal attempts.
exec python3 /app/skills/run_skill.py input_guard check_path_safety '{"path": "../../etc/passwd"}'
Filter sensitive data (API keys, passwords, tokens) from output text.
exec python3 /app/skills/run_skill.py input_guard filter_output '{"text": "key=sk-abc123"}'
Build a safe parameterized SQL query (select, insert, update).
exec python3 /app/skills/run_skill.py input_guard build_safe_query '{"table": "users", "operation": "select"}'
Get summary of recent security events including blocked requests and threat patterns.
exec python3 /app/skills/run_skill.py input_guard get_security_summary '{}'
Validate API parameters against a type schema.
exec python3 /app/skills/run_skill.py input_guard validate_api_params '{"params": {"limit": "10"}, "schema": {"limit": "integer"}}'
tools
# aria-working-memory Persistent short-term memory operations for Aria runtime context. ## Purpose - Store, retrieve, rank, checkpoint, and prune working memory. - Provide high-relevance context for decision and response flows. ## Main Tools - `remember` - `recall` - `get_context` - `checkpoint` - `restore_checkpoint` - `forget` - `update` - `reflect` - `sync_to_files`
development
```skill --- name: aria-unified-search description: "🔎 RRF-merged search across semantic + graph + memory backends" metadata: {"aria": {"emoji": "🔎"}} --- # aria-unified-search Unified search engine that queries semantic memories (pgvector cosine), knowledge graph (ILIKE), and traditional memories (text match), then merges results via Reciprocal Rank Fusion (RRF) with content-hash deduplication. ## Architecture ``` Query ↓ (parallel to 3 backends) ├── SemanticBackend (pgvector cosi
tools
# aria-telegram Telegram Bot API integration skill. ## Purpose - Send and reply to messages through bot credentials. - Fetch updates and basic bot metadata. ## Main Tools - `send_message` - `reply_to_message` - `get_updates` - `get_me`
tools
# aria-sprint-manager Sprint planning and board flow management skill. ## Purpose - Operate goal board as Product Owner. - Move, prioritize, and report sprint progress. ## Main Tools - `sprint_status` - `sprint_plan` - `sprint_move_goal` - `sprint_report` - `sprint_prioritize`