pp-setlist-fm

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of external software using npx -y and go install from the author's GitHub repository. Specifically, it downloads @mvanhorn/printing-press-library and binaries from github.com/mvanhorn/printing-press-library.
  • [DATA_EXFILTRATION]: The CLI supports a --deliver webhook:<url> flag, which allows tool output to be POSTed to an arbitrary external URL. Additionally, the feedback --send command can transmit local data stored in ~/.setlist-fm-pp-cli/feedback.jsonl to a remote endpoint if configured via environment variables.
  • [COMMAND_EXECUTION]: The skill's primary function is to execute a custom binary (setlist-fm-pp-cli) via the system shell. It also provides instructions for managing binary installation and verification within the shell environment using the Bash tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes artist and setlist information retrieved from the Setlist.fm API, which consists of crowd-sourced, externally-editable content.
  • Ingestion points: Data enters the agent context via artist, setlist, venue, and search commands targeting the external Setlist.fm database (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content are described for the fetched setlist data.
  • Capability inventory: The skill can execute shell commands (Bash) and perform network operations via the CLI's webhook feature.
  • Sanitization: While the CLI supports a --json output mode and --select for field filtering, there is no mention of sanitizing strings (e.g., song names) to prevent them from being interpreted as instructions by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 02:59 AM