skills/samihalawa/app-store-google-play-app-optimice-and-resubmit-autonomously-skill/app-store-google-play-optimice-and-resubmit-autonomously-skill/Gen Agent Trust Hub
app-store-google-play-optimice-and-resubmit-autonomously-skill
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to manipulate the agent's behavior during sensitive operations.
- Ingestion points: The skill reads full rejection messages and conversation history from App Store Connect, Google Play Console, and connected mailboxes via IMAP.
- Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore potentially malicious content embedded in reviewer feedback or emails.
- Capability inventory: The skill has extensive capabilities, including modifying application source code, performing build/archive operations, and executing network API calls to app store providers.
- Sanitization: Absent. There is no mention of sanitizing, escaping, or validating external content before it is used to drive implementation changes.
- [COMMAND_EXECUTION]: The skill is designed to execute shell commands to build and package applications.
- Evidence: The instructions direct the agent to "Archive, sign, export and upload through the existing release route," which involves executing local build toolchains.
- [CREDENTIALS_UNSAFE]: The skill relies on high-value secrets stored in the environment and local configuration files.
- Evidence: Accesses sensitive environment variables such as
ASC_KEY_PATH,PLAY_SERVICE_ACCOUNT_JSON, andREVENUECAT_SECRET_KEYfrom~/.envor the global environment. - Context: While necessary for the skill's purpose of app submission, these credentials represent a significant security surface if the agent is compromised via indirect injection.
- [DATA_EXPOSURE]: The skill accesses internal agent memory and history files.
- Evidence: Specifically reads from
~/.codex/skills/chronicle/SKILL.md,~/.codex/memories_extensions/chronicle/instructions.md, and~/.codex/screenpipe-memories.mdto reconstruct prior work.
Audit Metadata