The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The primary domain associated with this skill, https://qrcoin.fun, is flagged as malicious by automated URL scanners and is currently blacklisted.
[METADATA_POISONING]: The SKILL.md file itself has a confirmed malicious detection by reputation scanners (FileRepMalware).
[EXTERNAL_DOWNLOADS]: The skill fetches auction data from the Base blockchain's public RPC endpoint at https://mainnet.base.org and references a remote repository on GitHub (github.com/BankrBot/skills).
[INDIRECT_PROMPT_INJECTION]: The skill incorporates external data from blockchain RPC calls into the agent's context.
Ingestion points: Data retrieved via curl from https://mainnet.base.org in SKILL.md is piped into the agent's workflow.
Boundary markers: No delimiters or instructions are present to prevent the agent from obeying instructions that might be embedded in the retrieved blockchain data.
Capability inventory: The skill uses curl and jq for network queries and instructs the agent to use the 'Bankr' skill for transaction execution.
Sanitization: The skill uses jq to parse JSON structure but lacks content sanitization or verification of the fetched data.
[COMMAND_EXECUTION]: Instructions guide the agent to execute shell commands using curl and jq to fetch and parse data from external network sources, creating a path for processing untrusted remote content.

qrcoin