pp-espn

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the espn-pp-cli and espn-pp-mcp binaries from the author's GitHub repository (github.com/mvanhorn/printing-press-library) using go install and npx (via @mvanhorn/printing-press).- [COMMAND_EXECUTION]: Executes the espn-pp-cli binary to perform sports data lookups, local database synchronization, and system connectivity checks.- [DATA_EXFILTRATION]: Contains features designed to transmit data to external locations. The --deliver flag allows command results to be sent to arbitrary webhooks or local files. The feedback command also supports POSTing data to a remote server defined by the ESPN_FEEDBACK_ENDPOINT environment variable.- [PROMPT_INJECTION]: The skill processes untrusted sports data from ESPN's public endpoints, presenting a risk of indirect prompt injection. If the source data is manipulated to include malicious instructions, the agent may follow them.
  • Ingestion points: External API responses from ESPN fetched via espn-pp-cli.
  • Boundary markers: None present; the skill lacks delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill can perform file-write and network-send operations through the --deliver and feedback functionalities.
  • Sanitization: No explicit content validation or escaping of the sports data is provided beyond the use of field filtering via --select.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 07:12 PM