YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]
High
- Category
- YARA Match
- Confidence
- 80% confidence
- Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
- Content
python return "#" + v.upper() def mix(a, b, t): a, b = a.lstrip("#"), b.lstrip("#") ca = [int(a[i:i + 2], 16) for i in (0, 2, 4)] cb = [int(b[i:i + 2], 16) for i in (0, 2, 4)] return "#" + "".join(f"{round(x + (y - x) * t):02X}" for x, y in zip(ca, cb)) # ---------- rich text ---------- TOKEN = re.compile(r"(~~.+?~~|\*[^*]+?\*)") EMOJI = re.compile("[\U0001F000-\U0001FAFF☀-➿️]") def runs(text): """Split markup into words. Each word is a list of (text, accent, strike) pieces, so punctuation right after *accent* stays attached ("*twice*." renders as "twice."). A "\\n" word marks a line break.""" text = str(text or "") if EMOJI.search(text): warn("emoji removed from slide text (the bundled fonts have no emoji); put emoji in the caption") text = re.sub(r" {2,}", " ", EMOJI.sub("", text)).strip() text = smart_quotes(text) out = [] prev_tail_space = True for part in TOKEN.split(text): if not part: